X2��)�V)T���M#IuK��qfo�9n��J�A�nKJ��o5�-8���l:���� P���M ��� ���{��"1�_>Wj��l ���[���R�b.�J��<͛~"�� `
�j�fO8�i�a2��w����B�#�V�dn ��$MJp�c���"�� `]ܒ�@DMH '���;Kx�L�Gֽ �f���ڔ@HچR��h����Ƅ���i��A� �#%MF�q�� �B��7��� 4&����3W�]#5<�#%ݍZ�)i1iA:�D� D�:���� P��%)imIBMH��g&$31�}�A���[��њ�֊�Ą}���<:4�#qA@�{ܖ�4����mIoCS�i�+���P�_ܚ�4!4 ��>�.�n����@�"�֤h5!A2��=)Ak��Ƥ`�?A��p{R�ȚIH�9͜O�%��G�cH �j2B\kD�4���@�"�Q�d�Z�Ȍ��� psf�u�$5F@HɃ;_�.X!%+���I�`��<��邀R�b�H�F@HɃ;_�.X!%+���I�`��<��邀R�b�H�F@HɃ;_�.X!%+���I�`��<��邀R�b�H�F@HɃ;_�.X!%+���I�`� 3DE�A�Xs IEND�B`�
---
File: /docs/specification/2025-03-26/server/tools.md
---
---
title: Tools
type: docs
weight: 40
---
{{< callout type="info" >}} **Protocol Revision**: 2025-03-26 {{< /callout >}}
The Model Context Protocol (MCP) allows servers to expose tools that can be invoked by
language models. Tools enable models to interact with external systems, such as querying
databases, calling APIs, or performing computations. Each tool is uniquely identified by
a name and includes metadata describing its schema.
## User Interaction Model
Tools in MCP are designed to be **model-controlled**, meaning that the language model can
discover and invoke tools automatically based on its contextual understanding and the
user's prompts.
However, implementations are free to expose tools through any interface pattern that
suits their needs—the protocol itself does not mandate any specific user
interaction model.
{{< callout type="warning" >}} For trust & safety and security, there **SHOULD** always
be a human in the loop with the ability to deny tool invocations.
Applications **SHOULD**:
- Provide UI that makes clear which tools are being exposed to the AI model
- Insert clear visual indicators when tools are invoked
- Present confirmation prompts to the user for operations, to ensure a human is in the
loop {{< /callout >}}
## Capabilities
Servers that support tools **MUST** declare the `tools` capability:
```json
{
"capabilities": {
"tools": {
"listChanged": true
}
}
}
```
`listChanged` indicates whether the server will emit notifications when the list of
available tools changes.
## Protocol Messages
### Listing Tools
To discover available tools, clients send a `tools/list` request. This operation supports
[pagination]({{< ref "utilities/pagination" >}}).
**Request:**
```json
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/list",
"params": {
"cursor": "optional-cursor-value"
}
}
```
**Response:**
```json
{
"jsonrpc": "2.0",
"id": 1,
"result": {
"tools": [
{
"name": "get_weather",
"description": "Get current weather information for a location",
"inputSchema": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "City name or zip code"
}
},
"required": ["location"]
}
}
],
"nextCursor": "next-page-cursor"
}
}
```
### Calling Tools
To invoke a tool, clients send a `tools/call` request:
**Request:**
```json
{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/call",
"params": {
"name": "get_weather",
"arguments": {
"location": "New York"
}
}
}
```
**Response:**
```json
{
"jsonrpc": "2.0",
"id": 2,
"result": {
"content": [
{
"type": "text",
"text": "Current weather in New York:\nTemperature: 72°F\nConditions: Partly cloudy"
}
],
"isError": false
}
}
```
### List Changed Notification
When the list of available tools changes, servers that declared the `listChanged`
capability **SHOULD** send a notification:
```json
{
"jsonrpc": "2.0",
"method": "notifications/tools/list_changed"
}
```
## Message Flow
```mermaid
sequenceDiagram
participant LLM
participant Client
participant Server
Note over Client,Server: Discovery
Client->>Server: tools/list
Server-->>Client: List of tools
Note over Client,LLM: Tool Selection
LLM->>Client: Select tool to use
Note over Client,Server: Invocation
Client->>Server: tools/call
Server-->>Client: Tool result
Client->>LLM: Process result
Note over Client,Server: Updates
Server--)Client: tools/list_changed
Client->>Server: tools/list
Server-->>Client: Updated tools
```
## Data Types
### Tool
A tool definition includes:
- `name`: Unique identifier for the tool
- `description`: Human-readable description of functionality
- `inputSchema`: JSON Schema defining expected parameters
- `annotations`: optional properties describing tool behavior
{{< callout type="warning" >}} For trust & safety and security, clients **MUST** consider
tool annotations to be untrusted unless they come from trusted servers. {{< /callout >}}
### Tool Result
Tool results can contain multiple content items of different types:
#### Text Content
```json
{
"type": "text",
"text": "Tool result text"
}
```
#### Image Content
```json
{
"type": "image",
"data": "base64-encoded-data",
"mimeType": "image/png"
}
```
#### Audio Content
```json
{
"type": "audio",
"data": "base64-encoded-audio-data",
"mimeType": "audio/wav"
}
```
#### Embedded Resources
[Resources]({{< ref "resources" >}}) **MAY** be embedded, to provide additional context
or data, behind a URI that can be subscribed to or fetched again by the client later:
```json
{
"type": "resource",
"resource": {
"uri": "resource://example",
"mimeType": "text/plain",
"text": "Resource content"
}
}
```
## Error Handling
Tools use two error reporting mechanisms:
1. **Protocol Errors**: Standard JSON-RPC errors for issues like:
- Unknown tools
- Invalid arguments
- Server errors
2. **Tool Execution Errors**: Reported in tool results with `isError: true`:
- API failures
- Invalid input data
- Business logic errors
Example protocol error:
```json
{
"jsonrpc": "2.0",
"id": 3,
"error": {
"code": -32602,
"message": "Unknown tool: invalid_tool_name"
}
}
```
Example tool execution error:
```json
{
"jsonrpc": "2.0",
"id": 4,
"result": {
"content": [
{
"type": "text",
"text": "Failed to fetch weather data: API rate limit exceeded"
}
],
"isError": true
}
}
```
## Security Considerations
1. Servers **MUST**:
- Validate all tool inputs
- Implement proper access controls
- Rate limit tool invocations
- Sanitize tool outputs
2. Clients **SHOULD**:
- Prompt for user confirmation on sensitive operations
- Show tool inputs to the user before calling the server, to avoid malicious or
accidental data exfiltration
- Validate tool results before passing to LLM
- Implement timeouts for tool calls
- Log tool usage for audit purposes
---
File: /docs/specification/2025-03-26/_index.md
---
---
linkTitle: 2025-03-26 (Latest)
title: Model Context Protocol specification
cascade:
type: docs
breadcrumbs: false
weight: 1
aliases:
- /latest
---
{{< callout type="info" >}} **Protocol Revision**: 2025-03-26 {{< /callout >}}
[Model Context Protocol](https://modelcontextprotocol.io) (MCP) is an open protocol that
enables seamless integration between LLM applications and external data sources and
tools. Whether you're building an AI-powered IDE, enhancing a chat interface, or creating
custom AI workflows, MCP provides a standardized way to connect LLMs with the context
they need.
This specification defines the authoritative protocol requirements, based on the
TypeScript schema in
[schema.ts](https://github.com/modelcontextprotocol/specification/blob/main/schema/2025-03-26/schema.ts).
For implementation guides and examples, visit
[modelcontextprotocol.io](https://modelcontextprotocol.io).
The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD
NOT", "RECOMMENDED", "NOT RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be
interpreted as described in [BCP 14](https://datatracker.ietf.org/doc/html/bcp14)
[[RFC2119](https://datatracker.ietf.org/doc/html/rfc2119)]
[[RFC8174](https://datatracker.ietf.org/doc/html/rfc8174)] when, and only when, they
appear in all capitals, as shown here.
## Overview
MCP provides a standardized way for applications to:
- Share contextual information with language models
- Expose tools and capabilities to AI systems
- Build composable integrations and workflows
The protocol uses [JSON-RPC](https://www.jsonrpc.org/) 2.0 messages to establish
communication between:
- **Hosts**: LLM applications that initiate connections
- **Clients**: Connectors within the host application
- **Servers**: Services that provide context and capabilities
MCP takes some inspiration from the
[Language Server Protocol](https://microsoft.github.io/language-server-protocol/), which
standardizes how to add support for programming languages across a whole ecosystem of
development tools. In a similar way, MCP standardizes how to integrate additional context
and tools into the ecosystem of AI applications.
## Key Details
### Base Protocol
- [JSON-RPC](https://www.jsonrpc.org/) message format
- Stateful connections
- Server and client capability negotiation
### Features
Servers offer any of the following features to clients:
- **Resources**: Context and data, for the user or the AI model to use
- **Prompts**: Templated messages and workflows for users
- **Tools**: Functions for the AI model to execute
Clients may offer the following feature to servers:
- **Sampling**: Server-initiated agentic behaviors and recursive LLM interactions
### Additional Utilities
- Configuration
- Progress tracking
- Cancellation
- Error reporting
- Logging
## Security and Trust & Safety
The Model Context Protocol enables powerful capabilities through arbitrary data access
and code execution paths. With this power comes important security and trust
considerations that all implementors must carefully address.
### Key Principles
1. **User Consent and Control**
- Users must explicitly consent to and understand all data access and operations
- Users must retain control over what data is shared and what actions are taken
- Implementors should provide clear UIs for reviewing and authorizing activities
2. **Data Privacy**
- Hosts must obtain explicit user consent before exposing user data to servers
- Hosts must not transmit resource data elsewhere without user consent
- User data should be protected with appropriate access controls
3. **Tool Safety**
- Tools represent arbitrary code execution and must be treated with appropriate
caution.
- In particular, descriptions of tool behavior such as annotations should be
considered untrusted, unless obtained from a trusted server.
- Hosts must obtain explicit user consent before invoking any tool
- Users should understand what each tool does before authorizing its use
4. **LLM Sampling Controls**
- Users must explicitly approve any LLM sampling requests
- Users should control:
- Whether sampling occurs at all
- The actual prompt that will be sent
- What results the server can see
- The protocol intentionally limits server visibility into prompts
### Implementation Guidelines
While MCP itself cannot enforce these security principles at the protocol level,
implementors **SHOULD**:
1. Build robust consent and authorization flows into their applications
2. Provide clear documentation of security implications
3. Implement appropriate access controls and data protections
4. Follow security best practices in their integrations
5. Consider privacy implications in their feature designs
## Learn More
Explore the detailed specification for each protocol component:
{{< cards >}} {{< card link="architecture" title="Architecture" icon="template" >}}
{{< card link="basic" title="Base Protocol" icon="code" >}}
{{< card link="server" title="Server Features" icon="server" >}}
{{< card link="client" title="Client Features" icon="user" >}}
{{< card link="contributing" title="Contributing" icon="pencil" >}} {{< /cards >}}
---
File: /docs/specification/2025-03-26/changelog.md
---
---
title: Key Changes
type: docs
weight: 5
---
This document lists changes made to the Model Context Protocol (MCP) specification since
the previous revision, [2024-11-05]({{< ref "../2024-11-05" >}}).
## Major changes
1. Added a comprehensive **[authorization framework]({{< ref "basic/authorization" >}})**
based on OAuth 2.1 (PR
[#133](https://github.com/modelcontextprotocol/specification/pull/133))
1. Replaced the previous HTTP+SSE transport with a more flexible **[Streamable HTTP
transport]({{< ref "basic/transports#streamable-http" >}})** (PR
[#206](https://github.com/modelcontextprotocol/specification/pull/206))
1. Added support for JSON-RPC **[batching](https://www.jsonrpc.org/specification#batch)**
(PR [#228](https://github.com/modelcontextprotocol/specification/pull/228))
1. Added comprehensive **tool annotations** for better describing tool behavior, like
whether it is read-only or destructive (PR
[#185](https://github.com/modelcontextprotocol/specification/pull/185))
## Other schema changes
- Added `message` field to `ProgressNotification` to provide descriptive status updates
- Added support for audio data, joining the existing text and image content types
- Added `completions` capability to explicitly indicate support for argument
autocompletion suggestions
See
[the updated schema](http://github.com/modelcontextprotocol/specification/tree/main/schema/2025-03-26/schema.ts)
for more details.
## Full changelog
For a complete list of all changes that have been made since the last protocol revision,
[see GitHub](https://github.com/modelcontextprotocol/specification/compare/2024-11-05...2025-03-26).
---
File: /docs/specification/_index.md
---
---
title: Specification
cascade:
type: docs
breadcrumbs: false
weight: 10
---
---
File: /docs/specification/contributing.md
---
---
title: "Contributions"
weight: 20
cascade:
type: docs
breadcrumbs: false
---
We welcome contributions from the community! Please review our
[contributing guidelines](https://github.com/modelcontextprotocol/specification/blob/main/CONTRIBUTING.md)
for details on how to submit changes.
All contributors must adhere to our
[Code of Conduct](https://github.com/modelcontextprotocol/specification/blob/main/CODE_OF_CONDUCT.md).
For questions and discussions, please use
[GitHub Discussions](https://github.com/modelcontextprotocol/specification/discussions).
---
File: /docs/specification/versioning.md
---
---
title: Versioning
type: docs
weight: 10
---
The Model Context Protocol uses string-based version identifiers following the format
`YYYY-MM-DD`, to indicate the last date backwards incompatible changes were made.
{{< callout type="info" >}} The protocol version will _not_ be incremented when the
protocol is updated, as long as the changes maintain backwards compatibility. This allows
for incremental improvements while preserving interoperability. {{< /callout >}}
## Revisions
Revisions may be marked as:
- **Draft**: in-progress specifications, not yet ready for consumption.
- **Current**: the current protocol version, which is ready for use and may continue to
receive backwards compatible changes.
- **Final**: past, complete specifications that will not be changed.
The **current** protocol version is [**2025-03-26**]({{< ref "2025-03-26" >}}).
## Negotiation
Version negotiation happens during
[initialization]({{< ref "2025-03-26/basic/lifecycle#initialization" >}}). Clients and
servers **MAY** support multiple protocol versions simultaneously, but they **MUST**
agree on a single version to use for the session.
The protocol provides appropriate error handling if version negotiation fails, allowing
clients to gracefully terminate connections when they cannot find a version compatible
with the server.
---
File: /schema/2024-11-05/schema.ts
---
/* JSON-RPC types */
export type JSONRPCMessage =
| JSONRPCRequest
| JSONRPCNotification
| JSONRPCResponse
| JSONRPCError;
export const LATEST_PROTOCOL_VERSION = "2024-11-05";
export const JSONRPC_VERSION = "2.0";
/**
* A progress token, used to associate progress notifications with the original request.
*/
export type ProgressToken = string | number;
/**
* An opaque token used to represent a cursor for pagination.
*/
export type Cursor = string;
export interface Request {
method: string;
params?: {
_meta?: {
/**
* If specified, the caller is requesting out-of-band progress notifications for this request (as represented by notifications/progress). The value of this parameter is an opaque token that will be attached to any subsequent notifications. The receiver is not obligated to provide these notifications.
*/
progressToken?: ProgressToken;
};
[key: string]: unknown;
};
}
export interface Notification {
method: string;
params?: {
/**
* This parameter name is reserved by MCP to allow clients and servers to attach additional metadata to their notifications.
*/
_meta?: { [key: string]: unknown };
[key: string]: unknown;
};
}
export interface Result {
/**
* This result property is reserved by the protocol to allow clients and servers to attach additional metadata to their responses.
*/
_meta?: { [key: string]: unknown };
[key: string]: unknown;
}
/**
* A uniquely identifying ID for a request in JSON-RPC.
*/
export type RequestId = string | number;
/**
* A request that expects a response.
*/
export interface JSONRPCRequest extends Request {
jsonrpc: typeof JSONRPC_VERSION;
id: RequestId;
}
/**
* A notification which does not expect a response.
*/
export interface JSONRPCNotification extends Notification {
jsonrpc: typeof JSONRPC_VERSION;
}
/**
* A successful (non-error) response to a request.
*/
export interface JSONRPCResponse {
jsonrpc: typeof JSONRPC_VERSION;
id: RequestId;
result: Result;
}
// Standard JSON-RPC error codes
export const PARSE_ERROR = -32700;
export const INVALID_REQUEST = -32600;
export const METHOD_NOT_FOUND = -32601;
export const INVALID_PARAMS = -32602;
export const INTERNAL_ERROR = -32603;
/**
* A response to a request that indicates an error occurred.
*/
export interface JSONRPCError {
jsonrpc: typeof JSONRPC_VERSION;
id: RequestId;
error: {
/**
* The error type that occurred.
*/
code: number;
/**
* A short description of the error. The message SHOULD be limited to a concise single sentence.
*/
message: string;
/**
* Additional information about the error. The value of this member is defined by the sender (e.g. detailed error information, nested errors etc.).
*/
data?: unknown;
};
}
/* Empty result */
/**
* A response that indicates success but carries no data.
*/
export type EmptyResult = Result;
/* Cancellation */
/**
* This notification can be sent by either side to indicate that it is cancelling a previously-issued request.
*
* The request SHOULD still be in-flight, but due to communication latency, it is always possible that this notification MAY arrive after the request has already finished.
*
* This notification indicates that the result will be unused, so any associated processing SHOULD cease.
*
* A client MUST NOT attempt to cancel its `initialize` request.
*/
export interface CancelledNotification extends Notification {
method: "notifications/cancelled";
params: {
/**
* The ID of the request to cancel.
*
* This MUST correspond to the ID of a request previously issued in the same direction.
*/
requestId: RequestId;
/**
* An optional string describing the reason for the cancellation. This MAY be logged or presented to the user.
*/
reason?: string;
};
}
/* Initialization */
/**
* This request is sent from the client to the server when it first connects, asking it to begin initialization.
*/
export interface InitializeRequest extends Request {
method: "initialize";
params: {
/**
* The latest version of the Model Context Protocol that the client supports. The client MAY decide to support older versions as well.
*/
protocolVersion: string;
capabilities: ClientCapabilities;
clientInfo: Implementation;
};
}
/**
* After receiving an initialize request from the client, the server sends this response.
*/
export interface InitializeResult extends Result {
/**
* The version of the Model Context Protocol that the server wants to use. This may not match the version that the client requested. If the client cannot support this version, it MUST disconnect.
*/
protocolVersion: string;
capabilities: ServerCapabilities;
serverInfo: Implementation;
/**
* Instructions describing how to use the server and its features.
*
* This can be used by clients to improve the LLM's understanding of available tools, resources, etc. It can be thought of like a "hint" to the model. For example, this information MAY be added to the system prompt.
*/
instructions?: string;
}
/**
* This notification is sent from the client to the server after initialization has finished.
*/
export interface InitializedNotification extends Notification {
method: "notifications/initialized";
}
/**
* Capabilities a client may support. Known capabilities are defined here, in this schema, but this is not a closed set: any client can define its own, additional capabilities.
*/
export interface ClientCapabilities {
/**
* Experimental, non-standard capabilities that the client supports.
*/
experimental?: { [key: string]: object };
/**
* Present if the client supports listing roots.
*/
roots?: {
/**
* Whether the client supports notifications for changes to the roots list.
*/
listChanged?: boolean;
};
/**
* Present if the client supports sampling from an LLM.
*/
sampling?: object;
}
/**
* Capabilities that a server may support. Known capabilities are defined here, in this schema, but this is not a closed set: any server can define its own, additional capabilities.
*/
export interface ServerCapabilities {
/**
* Experimental, non-standard capabilities that the server supports.
*/
experimental?: { [key: string]: object };
/**
* Present if the server supports sending log messages to the client.
*/
logging?: object;
/**
* Present if the server offers any prompt templates.
*/
prompts?: {
/**
* Whether this server supports notifications for changes to the prompt list.
*/
listChanged?: boolean;
};
/**
* Present if the server offers any resources to read.
*/
resources?: {
/**
* Whether this server supports subscribing to resource updates.
*/
subscribe?: boolean;
/**
* Whether this server supports notifications for changes to the resource list.
*/
listChanged?: boolean;
};
/**
* Present if the server offers any tools to call.
*/
tools?: {
/**
* Whether this server supports notifications for changes to the tool list.
*/
listChanged?: boolean;
};
}
/**
* Describes the name and version of an MCP implementation.
*/
export interface Implementation {
name: string;
version: string;
}
/* Ping */
/**
* A ping, issued by either the server or the client, to check that the other party is still alive. The receiver must promptly respond, or else may be disconnected.
*/
export interface PingRequest extends Request {
method: "ping";
}
/* Progress notifications */
/**
* An out-of-band notification used to inform the receiver of a progress update for a long-running request.
*/
export interface ProgressNotification extends Notification {
method: "notifications/progress";
params: {
/**
* The progress token which was given in the initial request, used to associate this notification with the request that is proceeding.
*/
progressToken: ProgressToken;
/**
* The progress thus far. This should increase every time progress is made, even if the total is unknown.
*
* @TJS-type number
*/
progress: number;
/**
* Total number of items to process (or total progress required), if known.
*
* @TJS-type number
*/
total?: number;
};
}
/* Pagination */
export interface PaginatedRequest extends Request {
params?: {
/**
* An opaque token representing the current pagination position.
* If provided, the server should return results starting after this cursor.
*/
cursor?: Cursor;
};
}
export interface PaginatedResult extends Result {
/**
* An opaque token representing the pagination position after the last returned result.
* If present, there may be more results available.
*/
nextCursor?: Cursor;
}
/* Resources */
/**
* Sent from the client to request a list of resources the server has.
*/
export interface ListResourcesRequest extends PaginatedRequest {
method: "resources/list";
}
/**
* The server's response to a resources/list request from the client.
*/
export interface ListResourcesResult extends PaginatedResult {
resources: Resource[];
}
/**
* Sent from the client to request a list of resource templates the server has.
*/
export interface ListResourceTemplatesRequest extends PaginatedRequest {
method: "resources/templates/list";
}
/**
* The server's response to a resources/templates/list request from the client.
*/
export interface ListResourceTemplatesResult extends PaginatedResult {
resourceTemplates: ResourceTemplate[];
}
/**
* Sent from the client to the server, to read a specific resource URI.
*/
export interface ReadResourceRequest extends Request {
method: "resources/read";
params: {
/**
* The URI of the resource to read. The URI can use any protocol; it is up to the server how to interpret it.
*
* @format uri
*/
uri: string;
};
}
/**
* The server's response to a resources/read request from the client.
*/
export interface ReadResourceResult extends Result {
contents: (TextResourceContents | BlobResourceContents)[];
}
/**
* An optional notification from the server to the client, informing it that the list of resources it can read from has changed. This may be issued by servers without any previous subscription from the client.
*/
export interface ResourceListChangedNotification extends Notification {
method: "notifications/resources/list_changed";
}
/**
* Sent from the client to request resources/updated notifications from the server whenever a particular resource changes.
*/
export interface SubscribeRequest extends Request {
method: "resources/subscribe";
params: {
/**
* The URI of the resource to subscribe to. The URI can use any protocol; it is up to the server how to interpret it.
*
* @format uri
*/
uri: string;
};
}
/**
* Sent from the client to request cancellation of resources/updated notifications from the server. This should follow a previous resources/subscribe request.
*/
export interface UnsubscribeRequest extends Request {
method: "resources/unsubscribe";
params: {
/**
* The URI of the resource to unsubscribe from.
*
* @format uri
*/
uri: string;
};
}
/**
* A notification from the server to the client, informing it that a resource has changed and may need to be read again. This should only be sent if the client previously sent a resources/subscribe request.
*/
export interface ResourceUpdatedNotification extends Notification {
method: "notifications/resources/updated";
params: {
/**
* The URI of the resource that has been updated. This might be a sub-resource of the one that the client actually subscribed to.
*
* @format uri
*/
uri: string;
};
}
/**
* A known resource that the server is capable of reading.
*/
export interface Resource extends Annotated {
/**
* The URI of this resource.
*
* @format uri
*/
uri: string;
/**
* A human-readable name for this resource.
*
* This can be used by clients to populate UI elements.
*/
name: string;
/**
* A description of what this resource represents.
*
* This can be used by clients to improve the LLM's understanding of available resources. It can be thought of like a "hint" to the model.
*/
description?: string;
/**
* The MIME type of this resource, if known.
*/
mimeType?: string;
/**
* The size of the raw resource content, in bytes (i.e., before base64 encoding or any tokenization), if known.
*
* This can be used by Hosts to display file sizes and estimate context window usage.
*/
size?: number;
}
/**
* A template description for resources available on the server.
*/
export interface ResourceTemplate extends Annotated {
/**
* A URI template (according to RFC 6570) that can be used to construct resource URIs.
*
* @format uri-template
*/
uriTemplate: string;
/**
* A human-readable name for the type of resource this template refers to.
*
* This can be used by clients to populate UI elements.
*/
name: string;
/**
* A description of what this template is for.
*
* This can be used by clients to improve the LLM's understanding of available resources. It can be thought of like a "hint" to the model.
*/
description?: string;
/**
* The MIME type for all resources that match this template. This should only be included if all resources matching this template have the same type.
*/
mimeType?: string;
}
/**
* The contents of a specific resource or sub-resource.
*/
export interface ResourceContents {
/**
* The URI of this resource.
*
* @format uri
*/
uri: string;
/**
* The MIME type of this resource, if known.
*/
mimeType?: string;
}
export interface TextResourceContents extends ResourceContents {
/**
* The text of the item. This must only be set if the item can actually be represented as text (not binary data).
*/
text: string;
}
export interface BlobResourceContents extends ResourceContents {
/**
* A base64-encoded string representing the binary data of the item.
*
* @format byte
*/
blob: string;
}
/* Prompts */
/**
* Sent from the client to request a list of prompts and prompt templates the server has.
*/
export interface ListPromptsRequest extends PaginatedRequest {
method: "prompts/list";
}
/**
* The server's response to a prompts/list request from the client.
*/
export interface ListPromptsResult extends PaginatedResult {
prompts: Prompt[];
}
/**
* Used by the client to get a prompt provided by the server.
*/
export interface GetPromptRequest extends Request {
method: "prompts/get";
params: {
/**
* The name of the prompt or prompt template.
*/
name: string;
/**
* Arguments to use for templating the prompt.
*/
arguments?: { [key: string]: string };
};
}
/**
* The server's response to a prompts/get request from the client.
*/
export interface GetPromptResult extends Result {
/**
* An optional description for the prompt.
*/
description?: string;
messages: PromptMessage[];
}
/**
* A prompt or prompt template that the server offers.
*/
export interface Prompt {
/**
* The name of the prompt or prompt template.
*/
name: string;
/**
* An optional description of what this prompt provides
*/
description?: string;
/**
* A list of arguments to use for templating the prompt.
*/
arguments?: PromptArgument[];
}
/**
* Describes an argument that a prompt can accept.
*/
export interface PromptArgument {
/**
* The name of the argument.
*/
name: string;
/**
* A human-readable description of the argument.
*/
description?: string;
/**
* Whether this argument must be provided.
*/
required?: boolean;
}
/**
* The sender or recipient of messages and data in a conversation.
*/
export type Role = "user" | "assistant";
/**
* Describes a message returned as part of a prompt.
*
* This is similar to `SamplingMessage`, but also supports the embedding of
* resources from the MCP server.
*/
export interface PromptMessage {
role: Role;
content: TextContent | ImageContent | EmbeddedResource;
}
/**
* The contents of a resource, embedded into a prompt or tool call result.
*
* It is up to the client how best to render embedded resources for the benefit
* of the LLM and/or the user.
*/
export interface EmbeddedResource extends Annotated {
type: "resource";
resource: TextResourceContents | BlobResourceContents;
}
/**
* An optional notification from the server to the client, informing it that the list of prompts it offers has changed. This may be issued by servers without any previous subscription from the client.
*/
export interface PromptListChangedNotification extends Notification {
method: "notifications/prompts/list_changed";
}
/* Tools */
/**
* Sent from the client to request a list of tools the server has.
*/
export interface ListToolsRequest extends PaginatedRequest {
method: "tools/list";
}
/**
* The server's response to a tools/list request from the client.
*/
export interface ListToolsResult extends PaginatedResult {
tools: Tool[];
}
/**
* The server's response to a tool call.
*
* Any errors that originate from the tool SHOULD be reported inside the result
* object, with `isError` set to true, _not_ as an MCP protocol-level error
* response. Otherwise, the LLM would not be able to see that an error occurred
* and self-correct.
*
* However, any errors in _finding_ the tool, an error indicating that the
* server does not support tool calls, or any other exceptional conditions,
* should be reported as an MCP error response.
*/
export interface CallToolResult extends Result {
content: (TextContent | ImageContent | EmbeddedResource)[];
/**
* Whether the tool call ended in an error.
*
* If not set, this is assumed to be false (the call was successful).
*/
isError?: boolean;
}
/**
* Used by the client to invoke a tool provided by the server.
*/
export interface CallToolRequest extends Request {
method: "tools/call";
params: {
name: string;
arguments?: { [key: string]: unknown };
};
}
/**
* An optional notification from the server to the client, informing it that the list of tools it offers has changed. This may be issued by servers without any previous subscription from the client.
*/
export interface ToolListChangedNotification extends Notification {
method: "notifications/tools/list_changed";
}
/**
* Definition for a tool the client can call.
*/
export interface Tool {
/**
* The name of the tool.
*/
name: string;
/**
* A human-readable description of the tool.
*/
description?: string;
/**
* A JSON Schema object defining the expected parameters for the tool.
*/
inputSchema: {
type: "object";
properties?: { [key: string]: object };
required?: string[];
};
}
/* Logging */
/**
* A request from the client to the server, to enable or adjust logging.
*/
export interface SetLevelRequest extends Request {
method: "logging/setLevel";
params: {
/**
* The level of logging that the client wants to receive from the server. The server should send all logs at this level and higher (i.e., more severe) to the client as notifications/message.
*/
level: LoggingLevel;
};
}
/**
* Notification of a log message passed from server to client. If no logging/setLevel request has been sent from the client, the server MAY decide which messages to send automatically.
*/
export interface LoggingMessageNotification extends Notification {
method: "notifications/message";
params: {
/**
* The severity of this log message.
*/
level: LoggingLevel;
/**
* An optional name of the logger issuing this message.
*/
logger?: string;
/**
* The data to be logged, such as a string message or an object. Any JSON serializable type is allowed here.
*/
data: unknown;
};
}
/**
* The severity of a log message.
*
* These map to syslog message severities, as specified in RFC-5424:
* https://datatracker.ietf.org/doc/html/rfc5424#section-6.2.1
*/
export type LoggingLevel =
| "debug"
| "info"
| "notice"
| "warning"
| "error"
| "critical"
| "alert"
| "emergency";
/* Sampling */
/**
* A request from the server to sample an LLM via the client. The client has full discretion over which model to select. The client should also inform the user before beginning sampling, to allow them to inspect the request (human in the loop) and decide whether to approve it.
*/
export interface CreateMessageRequest extends Request {
method: "sampling/createMessage";
params: {
messages: SamplingMessage[];
/**
* The server's preferences for which model to select. The client MAY ignore these preferences.
*/
modelPreferences?: ModelPreferences;
/**
* An optional system prompt the server wants to use for sampling. The client MAY modify or omit this prompt.
*/
systemPrompt?: string;
/**
* A request to include context from one or more MCP servers (including the caller), to be attached to the prompt. The client MAY ignore this request.
*/
includeContext?: "none" | "thisServer" | "allServers";
/**
* @TJS-type number
*/
temperature?: number;
/**
* The maximum number of tokens to sample, as requested by the server. The client MAY choose to sample fewer tokens than requested.
*/
maxTokens: number;
stopSequences?: string[];
/**
* Optional metadata to pass through to the LLM provider. The format of this metadata is provider-specific.
*/
metadata?: object;
};
}
/**
* The client's response to a sampling/create_message request from the server. The client should inform the user before returning the sampled message, to allow them to inspect the response (human in the loop) and decide whether to allow the server to see it.
*/
export interface CreateMessageResult extends Result, SamplingMessage {
/**
* The name of the model that generated the message.
*/
model: string;
/**
* The reason why sampling stopped, if known.
*/
stopReason?: "endTurn" | "stopSequence" | "maxTokens" | string;
}
/**
* Describes a message issued to or received from an LLM API.
*/
export interface SamplingMessage {
role: Role;
content: TextContent | ImageContent;
}
/**
* Base for objects that include optional annotations for the client. The client can use annotations to inform how objects are used or displayed
*/
export interface Annotated {
annotations?: {
/**
* Describes who the intended customer of this object or data is.
*
* It can include multiple entries to indicate content useful for multiple audiences (e.g., `["user", "assistant"]`).
*/
audience?: Role[];
/**
* Describes how important this data is for operating the server.
*
* A value of 1 means "most important," and indicates that the data is
* effectively required, while 0 means "least important," and indicates that
* the data is entirely optional.
*
* @TJS-type number
* @minimum 0
* @maximum 1
*/
priority?: number;
}
}
/**
* Text provided to or from an LLM.
*/
export interface TextContent extends Annotated {
type: "text";
/**
* The text content of the message.
*/
text: string;
}
/**
* An image provided to or from an LLM.
*/
export interface ImageContent extends Annotated {
type: "image";
/**
* The base64-encoded image data.
*
* @format byte
*/
data: string;
/**
* The MIME type of the image. Different providers may support different image types.
*/
mimeType: string;
}
/**
* The server's preferences for model selection, requested of the client during sampling.
*
* Because LLMs can vary along multiple dimensions, choosing the "best" model is
* rarely straightforward. Different models excel in different areas—some are
* faster but less capable, others are more capable but more expensive, and so
* on. This interface allows servers to express their priorities across multiple
* dimensions to help clients make an appropriate selection for their use case.
*
* These preferences are always advisory. The client MAY ignore them. It is also
* up to the client to decide how to interpret these preferences and how to
* balance them against other considerations.
*/
export interface ModelPreferences {
/**
* Optional hints to use for model selection.
*
* If multiple hints are specified, the client MUST evaluate them in order
* (such that the first match is taken).
*
* The client SHOULD prioritize these hints over the numeric priorities, but
* MAY still use the priorities to select from ambiguous matches.
*/
hints?: ModelHint[];
/**
* How much to prioritize cost when selecting a model. A value of 0 means cost
* is not important, while a value of 1 means cost is the most important
* factor.
*
* @TJS-type number
* @minimum 0
* @maximum 1
*/
costPriority?: number;
/**
* How much to prioritize sampling speed (latency) when selecting a model. A
* value of 0 means speed is not important, while a value of 1 means speed is
* the most important factor.
*
* @TJS-type number
* @minimum 0
* @maximum 1
*/
speedPriority?: number;
/**
* How much to prioritize intelligence and capabilities when selecting a
* model. A value of 0 means intelligence is not important, while a value of 1
* means intelligence is the most important factor.
*
* @TJS-type number
* @minimum 0
* @maximum 1
*/
intelligencePriority?: number;
}
/**
* Hints to use for model selection.
*
* Keys not declared here are currently left unspecified by the spec and are up
* to the client to interpret.
*/
export interface ModelHint {
/**
* A hint for a model name.
*
* The client SHOULD treat this as a substring of a model name; for example:
* - `claude-3-5-sonnet` should match `claude-3-5-sonnet-20241022`
* - `sonnet` should match `claude-3-5-sonnet-20241022`, `claude-3-sonnet-20240229`, etc.
* - `claude` should match any Claude model
*
* The client MAY also map the string to a different provider's model name or a different model family, as long as it fills a similar niche; for example:
* - `gemini-1.5-flash` could match `claude-3-haiku-20240307`
*/
name?: string;
}
/* Autocomplete */
/**
* A request from the client to the server, to ask for completion options.
*/
export interface CompleteRequest extends Request {
method: "completion/complete";
params: {
ref: PromptReference | ResourceReference;
/**
* The argument's information
*/
argument: {
/**
* The name of the argument
*/
name: string;
/**
* The value of the argument to use for completion matching.
*/
value: string;
};
};
}
/**
* The server's response to a completion/complete request
*/
export interface CompleteResult extends Result {
completion: {
/**
* An array of completion values. Must not exceed 100 items.
*/
values: string[];
/**
* The total number of completion options available. This can exceed the number of values actually sent in the response.
*/
total?: number;
/**
* Indicates whether there are additional completion options beyond those provided in the current response, even if the exact total is unknown.
*/
hasMore?: boolean;
};
}
/**
* A reference to a resource or resource template definition.
*/
export interface ResourceReference {
type: "ref/resource";
/**
* The URI or URI template of the resource.
*
* @format uri-template
*/
uri: string;
}
/**
* Identifies a prompt.
*/
export interface PromptReference {
type: "ref/prompt";
/**
* The name of the prompt or prompt template
*/
name: string;
}
/* Roots */
/**
* Sent from the server to request a list of root URIs from the client. Roots allow
* servers to ask for specific directories or files to operate on. A common example
* for roots is providing a set of repositories or directories a server should operate
* on.
*
* This request is typically used when the server needs to understand the file system
* structure or access specific locations that the client has permission to read from.
*/
export interface ListRootsRequest extends Request {
method: "roots/list";
}
/**
* The client's response to a roots/list request from the server.
* This result contains an array of Root objects, each representing a root directory
* or file that the server can operate on.
*/
export interface ListRootsResult extends Result {
roots: Root[];
}
/**
* Represents a root directory or file that the server can operate on.
*/
export interface Root {
/**
* The URI identifying the root. This *must* start with file:// for now.
* This restriction may be relaxed in future versions of the protocol to allow
* other URI schemes.
*
* @format uri
*/
uri: string;
/**
* An optional name for the root. This can be used to provide a human-readable
* identifier for the root, which may be useful for display purposes or for
* referencing the root in other parts of the application.
*/
name?: string;
}
/**
* A notification from the client to the server, informing it that the list of roots has changed.
* This notification should be sent whenever the client adds, removes, or modifies any root.
* The server should then request an updated list of roots using the ListRootsRequest.
*/
export interface RootsListChangedNotification extends Notification {
method: "notifications/roots/list_changed";
}
/* Client messages */
export type ClientRequest =
| PingRequest
| InitializeRequest
| CompleteRequest
| SetLevelRequest
| GetPromptRequest
| ListPromptsRequest
| ListResourcesRequest
| ListResourceTemplatesRequest
| ReadResourceRequest
| SubscribeRequest
| UnsubscribeRequest
| CallToolRequest
| ListToolsRequest;
export type ClientNotification =
| CancelledNotification
| ProgressNotification
| InitializedNotification
| RootsListChangedNotification;
export type ClientResult = EmptyResult | CreateMessageResult | ListRootsResult;
/* Server messages */
export type ServerRequest =
| PingRequest
| CreateMessageRequest
| ListRootsRequest;
export type ServerNotification =
| CancelledNotification
| ProgressNotification
| LoggingMessageNotification
| ResourceUpdatedNotification
| ResourceListChangedNotification
| ToolListChangedNotification
| PromptListChangedNotification;
export type ServerResult =
| EmptyResult
| InitializeResult
| CompleteResult
| GetPromptResult
| ListPromptsResult
| ListResourcesResult
| ListResourceTemplatesResult
| ReadResourceResult
| CallToolResult
| ListToolsResult;
---
File: /schema/2025-03-26/schema.ts
---
/* JSON-RPC types */
/**
* Refers to any valid JSON-RPC object that can be decoded off the wire, or encoded to be sent.
*/
export type JSONRPCMessage =
| JSONRPCRequest
| JSONRPCNotification
| JSONRPCBatchRequest
| JSONRPCResponse
| JSONRPCError
| JSONRPCBatchResponse;
/**
* A JSON-RPC batch request, as described in https://www.jsonrpc.org/specification#batch.
*/
export type JSONRPCBatchRequest = (JSONRPCRequest | JSONRPCNotification)[];
/**
* A JSON-RPC batch response, as described in https://www.jsonrpc.org/specification#batch.
*/
export type JSONRPCBatchResponse = (JSONRPCResponse | JSONRPCError)[];
export const LATEST_PROTOCOL_VERSION = "2025-03-26";
export const JSONRPC_VERSION = "2.0";
/**
* A progress token, used to associate progress notifications with the original request.
*/
export type ProgressToken = string | number;
/**
* An opaque token used to represent a cursor for pagination.
*/
export type Cursor = string;
export interface Request {
method: string;
params?: {
_meta?: {
/**
* If specified, the caller is requesting out-of-band progress notifications for this request (as represented by notifications/progress). The value of this parameter is an opaque token that will be attached to any subsequent notifications. The receiver is not obligated to provide these notifications.
*/
progressToken?: ProgressToken;
};
[key: string]: unknown;
};
}
export interface Notification {
method: string;
params?: {
/**
* This parameter name is reserved by MCP to allow clients and servers to attach additional metadata to their notifications.
*/
_meta?: { [key: string]: unknown };
[key: string]: unknown;
};
}
export interface Result {
/**
* This result property is reserved by the protocol to allow clients and servers to attach additional metadata to their responses.
*/
_meta?: { [key: string]: unknown };
[key: string]: unknown;
}
/**
* A uniquely identifying ID for a request in JSON-RPC.
*/
export type RequestId = string | number;
/**
* A request that expects a response.
*/
export interface JSONRPCRequest extends Request {
jsonrpc: typeof JSONRPC_VERSION;
id: RequestId;
}
/**
* A notification which does not expect a response.
*/
export interface JSONRPCNotification extends Notification {
jsonrpc: typeof JSONRPC_VERSION;
}
/**
* A successful (non-error) response to a request.
*/
export interface JSONRPCResponse {
jsonrpc: typeof JSONRPC_VERSION;
id: RequestId;
result: Result;
}
// Standard JSON-RPC error codes
export const PARSE_ERROR = -32700;
export const INVALID_REQUEST = -32600;
export const METHOD_NOT_FOUND = -32601;
export const INVALID_PARAMS = -32602;
export const INTERNAL_ERROR = -32603;
/**
* A response to a request that indicates an error occurred.
*/
export interface JSONRPCError {
jsonrpc: typeof JSONRPC_VERSION;
id: RequestId;
error: {
/**
* The error type that occurred.
*/
code: number;
/**
* A short description of the error. The message SHOULD be limited to a concise single sentence.
*/
message: string;
/**
* Additional information about the error. The value of this member is defined by the sender (e.g. detailed error information, nested errors etc.).
*/
data?: unknown;
};
}
/* Empty result */
/**
* A response that indicates success but carries no data.
*/
export type EmptyResult = Result;
/* Cancellation */
/**
* This notification can be sent by either side to indicate that it is cancelling a previously-issued request.
*
* The request SHOULD still be in-flight, but due to communication latency, it is always possible that this notification MAY arrive after the request has already finished.
*
* This notification indicates that the result will be unused, so any associated processing SHOULD cease.
*
* A client MUST NOT attempt to cancel its `initialize` request.
*/
export interface CancelledNotification extends Notification {
method: "notifications/cancelled";
params: {
/**
* The ID of the request to cancel.
*
* This MUST correspond to the ID of a request previously issued in the same direction.
*/
requestId: RequestId;
/**
* An optional string describing the reason for the cancellation. This MAY be logged or presented to the user.
*/
reason?: string;
};
}
/* Initialization */
/**
* This request is sent from the client to the server when it first connects, asking it to begin initialization.
*/
export interface InitializeRequest extends Request {
method: "initialize";
params: {
/**
* The latest version of the Model Context Protocol that the client supports. The client MAY decide to support older versions as well.
*/
protocolVersion: string;
capabilities: ClientCapabilities;
clientInfo: Implementation;
};
}
/**
* After receiving an initialize request from the client, the server sends this response.
*/
export interface InitializeResult extends Result {
/**
* The version of the Model Context Protocol that the server wants to use. This may not match the version that the client requested. If the client cannot support this version, it MUST disconnect.
*/
protocolVersion: string;
capabilities: ServerCapabilities;
serverInfo: Implementation;
/**
* Instructions describing how to use the server and its features.
*
* This can be used by clients to improve the LLM's understanding of available tools, resources, etc. It can be thought of like a "hint" to the model. For example, this information MAY be added to the system prompt.
*/
instructions?: string;
}
/**
* This notification is sent from the client to the server after initialization has finished.
*/
export interface InitializedNotification extends Notification {
method: "notifications/initialized";
}
/**
* Capabilities a client may support. Known capabilities are defined here, in this schema, but this is not a closed set: any client can define its own, additional capabilities.
*/
export interface ClientCapabilities {
/**
* Experimental, non-standard capabilities that the client supports.
*/
experimental?: { [key: string]: object };
/**
* Present if the client supports listing roots.
*/
roots?: {
/**
* Whether the client supports notifications for changes to the roots list.
*/
listChanged?: boolean;
};
/**
* Present if the client supports sampling from an LLM.
*/
sampling?: object;
}
/**
* Capabilities that a server may support. Known capabilities are defined here, in this schema, but this is not a closed set: any server can define its own, additional capabilities.
*/
export interface ServerCapabilities {
/**
* Experimental, non-standard capabilities that the server supports.
*/
experimental?: { [key: string]: object };
/**
* Present if the server supports sending log messages to the client.
*/
logging?: object;
/**
* Present if the server supports argument autocompletion suggestions.
*/
completions?: object;
/**
* Present if the server offers any prompt templates.
*/
prompts?: {
/**
* Whether this server supports notifications for changes to the prompt list.
*/
listChanged?: boolean;
};
/**
* Present if the server offers any resources to read.
*/
resources?: {
/**
* Whether this server supports subscribing to resource updates.
*/
subscribe?: boolean;
/**
* Whether this server supports notifications for changes to the resource list.
*/
listChanged?: boolean;
};
/**
* Present if the server offers any tools to call.
*/
tools?: {
/**
* Whether this server supports notifications for changes to the tool list.
*/
listChanged?: boolean;
};
}
/**
* Describes the name and version of an MCP implementation.
*/
export interface Implementation {
name: string;
version: string;
}
/* Ping */
/**
* A ping, issued by either the server or the client, to check that the other party is still alive. The receiver must promptly respond, or else may be disconnected.
*/
export interface PingRequest extends Request {
method: "ping";
}
/* Progress notifications */
/**
* An out-of-band notification used to inform the receiver of a progress update for a long-running request.
*/
export interface ProgressNotification extends Notification {
method: "notifications/progress";
params: {
/**
* The progress token which was given in the initial request, used to associate this notification with the request that is proceeding.
*/
progressToken: ProgressToken;
/**
* The progress thus far. This should increase every time progress is made, even if the total is unknown.
*
* @TJS-type number
*/
progress: number;
/**
* Total number of items to process (or total progress required), if known.
*
* @TJS-type number
*/
total?: number;
/**
* An optional message describing the current progress.
*/
message?: string;
};
}
/* Pagination */
export interface PaginatedRequest extends Request {
params?: {
/**
* An opaque token representing the current pagination position.
* If provided, the server should return results starting after this cursor.
*/
cursor?: Cursor;
};
}
export interface PaginatedResult extends Result {
/**
* An opaque token representing the pagination position after the last returned result.
* If present, there may be more results available.
*/
nextCursor?: Cursor;
}
/* Resources */
/**
* Sent from the client to request a list of resources the server has.
*/
export interface ListResourcesRequest extends PaginatedRequest {
method: "resources/list";
}
/**
* The server's response to a resources/list request from the client.
*/
export interface ListResourcesResult extends PaginatedResult {
resources: Resource[];
}
/**
* Sent from the client to request a list of resource templates the server has.
*/
export interface ListResourceTemplatesRequest extends PaginatedRequest {
method: "resources/templates/list";
}
/**
* The server's response to a resources/templates/list request from the client.
*/
export interface ListResourceTemplatesResult extends PaginatedResult {
resourceTemplates: ResourceTemplate[];
}
/**
* Sent from the client to the server, to read a specific resource URI.
*/
export interface ReadResourceRequest extends Request {
method: "resources/read";
params: {
/**
* The URI of the resource to read. The URI can use any protocol; it is up to the server how to interpret it.
*
* @format uri
*/
uri: string;
};
}
/**
* The server's response to a resources/read request from the client.
*/
export interface ReadResourceResult extends Result {
contents: (TextResourceContents | BlobResourceContents)[];
}
/**
* An optional notification from the server to the client, informing it that the list of resources it can read from has changed. This may be issued by servers without any previous subscription from the client.
*/
export interface ResourceListChangedNotification extends Notification {
method: "notifications/resources/list_changed";
}
/**
* Sent from the client to request resources/updated notifications from the server whenever a particular resource changes.
*/
export interface SubscribeRequest extends Request {
method: "resources/subscribe";
params: {
/**
* The URI of the resource to subscribe to. The URI can use any protocol; it is up to the server how to interpret it.
*
* @format uri
*/
uri: string;
};
}
/**
* Sent from the client to request cancellation of resources/updated notifications from the server. This should follow a previous resources/subscribe request.
*/
export interface UnsubscribeRequest extends Request {
method: "resources/unsubscribe";
params: {
/**
* The URI of the resource to unsubscribe from.
*
* @format uri
*/
uri: string;
};
}
/**
* A notification from the server to the client, informing it that a resource has changed and may need to be read again. This should only be sent if the client previously sent a resources/subscribe request.
*/
export interface ResourceUpdatedNotification extends Notification {
method: "notifications/resources/updated";
params: {
/**
* The URI of the resource that has been updated. This might be a sub-resource of the one that the client actually subscribed to.
*
* @format uri
*/
uri: string;
};
}
/**
* A known resource that the server is capable of reading.
*/
export interface Resource {
/**
* The URI of this resource.
*
* @format uri
*/
uri: string;
/**
* A human-readable name for this resource.
*
* This can be used by clients to populate UI elements.
*/
name: string;
/**
* A description of what this resource represents.
*
* This can be used by clients to improve the LLM's understanding of available resources. It can be thought of like a "hint" to the model.
*/
description?: string;
/**
* The MIME type of this resource, if known.
*/
mimeType?: string;
/**
* Optional annotations for the client.
*/
annotations?: Annotations;
}
/**
* A template description for resources available on the server.
*/
export interface ResourceTemplate {
/**
* A URI template (according to RFC 6570) that can be used to construct resource URIs.
*
* @format uri-template
*/
uriTemplate: string;
/**
* A human-readable name for the type of resource this template refers to.
*
* This can be used by clients to populate UI elements.
*/
name: string;
/**
* A description of what this template is for.
*
* This can be used by clients to improve the LLM's understanding of available resources. It can be thought of like a "hint" to the model.
*/
description?: string;
/**
* The MIME type for all resources that match this template. This should only be included if all resources matching this template have the same type.
*/
mimeType?: string;
/**
* Optional annotations for the client.
*/
annotations?: Annotations;
}
/**
* The contents of a specific resource or sub-resource.
*/
export interface ResourceContents {
/**
* The URI of this resource.
*
* @format uri
*/
uri: string;
/**
* The MIME type of this resource, if known.
*/
mimeType?: string;
}
export interface TextResourceContents extends ResourceContents {
/**
* The text of the item. This must only be set if the item can actually be represented as text (not binary data).
*/
text: string;
}
export interface BlobResourceContents extends ResourceContents {
/**
* A base64-encoded string representing the binary data of the item.
*
* @format byte
*/
blob: string;
}
/* Prompts */
/**
* Sent from the client to request a list of prompts and prompt templates the server has.
*/
export interface ListPromptsRequest extends PaginatedRequest {
method: "prompts/list";
}
/**
* The server's response to a prompts/list request from the client.
*/
export interface ListPromptsResult extends PaginatedResult {
prompts: Prompt[];
}
/**
* Used by the client to get a prompt provided by the server.
*/
export interface GetPromptRequest extends Request {
method: "prompts/get";
params: {
/**
* The name of the prompt or prompt template.
*/
name: string;
/**
* Arguments to use for templating the prompt.
*/
arguments?: { [key: string]: string };
};
}
/**
* The server's response to a prompts/get request from the client.
*/
export interface GetPromptResult extends Result {
/**
* An optional description for the prompt.
*/
description?: string;
messages: PromptMessage[];
}
/**
* A prompt or prompt template that the server offers.
*/
export interface Prompt {
/**
* The name of the prompt or prompt template.
*/
name: string;
/**
* An optional description of what this prompt provides
*/
description?: string;
/**
* A list of arguments to use for templating the prompt.
*/
arguments?: PromptArgument[];
}
/**
* Describes an argument that a prompt can accept.
*/
export interface PromptArgument {
/**
* The name of the argument.
*/
name: string;
/**
* A human-readable description of the argument.
*/
description?: string;
/**
* Whether this argument must be provided.
*/
required?: boolean;
}
/**
* The sender or recipient of messages and data in a conversation.
*/
export type Role = "user" | "assistant";
/**
* Describes a message returned as part of a prompt.
*
* This is similar to `SamplingMessage`, but also supports the embedding of
* resources from the MCP server.
*/
export interface PromptMessage {
role: Role;
content: TextContent | ImageContent | AudioContent | EmbeddedResource;
}
/**
* The contents of a resource, embedded into a prompt or tool call result.
*
* It is up to the client how best to render embedded resources for the benefit
* of the LLM and/or the user.
*/
export interface EmbeddedResource {
type: "resource";
resource: TextResourceContents | BlobResourceContents;
/**
* Optional annotations for the client.
*/
annotations?: Annotations;
}
/**
* An optional notification from the server to the client, informing it that the list of prompts it offers has changed. This may be issued by servers without any previous subscription from the client.
*/
export interface PromptListChangedNotification extends Notification {
method: "notifications/prompts/list_changed";
}
/* Tools */
/**
* Sent from the client to request a list of tools the server has.
*/
export interface ListToolsRequest extends PaginatedRequest {
method: "tools/list";
}
/**
* The server's response to a tools/list request from the client.
*/
export interface ListToolsResult extends PaginatedResult {
tools: Tool[];
}
/**
* The server's response to a tool call.
*
* Any errors that originate from the tool SHOULD be reported inside the result
* object, with `isError` set to true, _not_ as an MCP protocol-level error
* response. Otherwise, the LLM would not be able to see that an error occurred
* and self-correct.
*
* However, any errors in _finding_ the tool, an error indicating that the
* server does not support tool calls, or any other exceptional conditions,
* should be reported as an MCP error response.
*/
export interface CallToolResult extends Result {
content: (TextContent | ImageContent | AudioContent | EmbeddedResource)[];
/**
* Whether the tool call ended in an error.
*
* If not set, this is assumed to be false (the call was successful).
*/
isError?: boolean;
}
/**
* Used by the client to invoke a tool provided by the server.
*/
export interface CallToolRequest extends Request {
method: "tools/call";
params: {
name: string;
arguments?: { [key: string]: unknown };
};
}
/**
* An optional notification from the server to the client, informing it that the list of tools it offers has changed. This may be issued by servers without any previous subscription from the client.
*/
export interface ToolListChangedNotification extends Notification {
method: "notifications/tools/list_changed";
}
/**
* Additional properties describing a Tool to clients.
*
* NOTE: all properties in ToolAnnotations are **hints**.
* They are not guaranteed to provide a faithful description of
* tool behavior (including descriptive properties like `title`).
*
* Clients should never make tool use decisions based on ToolAnnotations
* received from untrusted servers.
*/
export interface ToolAnnotations {
/**
* A human-readable title for the tool.
*/
title?: string;
/**
* If true, the tool does not modify its environment.
*
* Default: false
*/
readOnlyHint?: boolean;
/**
* If true, the tool may perform destructive updates to its environment.
* If false, the tool performs only additive updates.
*
* (This property is meaningful only when `readOnlyHint == false`)
*
* Default: true
*/
destructiveHint?: boolean;
/**
* If true, calling the tool repeatedly with the same arguments
* will have no additional effect on the its environment.
*
* (This property is meaningful only when `readOnlyHint == false`)
*
* Default: false
*/
idempotentHint?: boolean;
/**
* If true, this tool may interact with an "open world" of external
* entities. If false, the tool's domain of interaction is closed.
* For example, the world of a web search tool is open, whereas that
* of a memory tool is not.
*
* Default: true
*/
openWorldHint?: boolean;
}
/**
* Definition for a tool the client can call.
*/
export interface Tool {
/**
* The name of the tool.
*/
name: string;
/**
* A human-readable description of the tool.
*
* This can be used by clients to improve the LLM's understanding of available tools. It can be thought of like a "hint" to the model.
*/
description?: string;
/**
* A JSON Schema object defining the expected parameters for the tool.
*/
inputSchema: {
type: "object";
properties?: { [key: string]: object };
required?: string[];
};
/**
* Optional additional tool information.
*/
annotations?: ToolAnnotations;
}
/* Logging */
/**
* A request from the client to the server, to enable or adjust logging.
*/
export interface SetLevelRequest extends Request {
method: "logging/setLevel";
params: {
/**
* The level of logging that the client wants to receive from the server. The server should send all logs at this level and higher (i.e., more severe) to the client as notifications/message.
*/
level: LoggingLevel;
};
}
/**
* Notification of a log message passed from server to client. If no logging/setLevel request has been sent from the client, the server MAY decide which messages to send automatically.
*/
export interface LoggingMessageNotification extends Notification {
method: "notifications/message";
params: {
/**
* The severity of this log message.
*/
level: LoggingLevel;
/**
* An optional name of the logger issuing this message.
*/
logger?: string;
/**
* The data to be logged, such as a string message or an object. Any JSON serializable type is allowed here.
*/
data: unknown;
};
}
/**
* The severity of a log message.
*
* These map to syslog message severities, as specified in RFC-5424:
* https://datatracker.ietf.org/doc/html/rfc5424#section-6.2.1
*/
export type LoggingLevel =
| "debug"
| "info"
| "notice"
| "warning"
| "error"
| "critical"
| "alert"
| "emergency";
/* Sampling */
/**
* A request from the server to sample an LLM via the client. The client has full discretion over which model to select. The client should also inform the user before beginning sampling, to allow them to inspect the request (human in the loop) and decide whether to approve it.
*/
export interface CreateMessageRequest extends Request {
method: "sampling/createMessage";
params: {
messages: SamplingMessage[];
/**
* The server's preferences for which model to select. The client MAY ignore these preferences.
*/
modelPreferences?: ModelPreferences;
/**
* An optional system prompt the server wants to use for sampling. The client MAY modify or omit this prompt.
*/
systemPrompt?: string;
/**
* A request to include context from one or more MCP servers (including the caller), to be attached to the prompt. The client MAY ignore this request.
*/
includeContext?: "none" | "thisServer" | "allServers";
/**
* @TJS-type number
*/
temperature?: number;
/**
* The maximum number of tokens to sample, as requested by the server. The client MAY choose to sample fewer tokens than requested.
*/
maxTokens: number;
stopSequences?: string[];
/**
* Optional metadata to pass through to the LLM provider. The format of this metadata is provider-specific.
*/
metadata?: object;
};
}
/**
* The client's response to a sampling/create_message request from the server. The client should inform the user before returning the sampled message, to allow them to inspect the response (human in the loop) and decide whether to allow the server to see it.
*/
export interface CreateMessageResult extends Result, SamplingMessage {
/**
* The name of the model that generated the message.
*/
model: string;
/**
* The reason why sampling stopped, if known.
*/
stopReason?: "endTurn" | "stopSequence" | "maxTokens" | string;
}
/**
* Describes a message issued to or received from an LLM API.
*/
export interface SamplingMessage {
role: Role;
content: TextContent | ImageContent | AudioContent;
}
/**
* Optional annotations for the client. The client can use annotations to inform how objects are used or displayed
*/
export interface Annotations {
/**
* Describes who the intended customer of this object or data is.
*
* It can include multiple entries to indicate content useful for multiple audiences (e.g., `["user", "assistant"]`).
*/
audience?: Role[];
/**
* Describes how important this data is for operating the server.
*
* A value of 1 means "most important," and indicates that the data is
* effectively required, while 0 means "least important," and indicates that
* the data is entirely optional.
*
* @TJS-type number
* @minimum 0
* @maximum 1
*/
priority?: number;
}
/**
* Text provided to or from an LLM.
*/
export interface TextContent {
type: "text";
/**
* The text content of the message.
*/
text: string;
/**
* Optional annotations for the client.
*/
annotations?: Annotations;
}
/**
* An image provided to or from an LLM.
*/
export interface ImageContent {
type: "image";
/**
* The base64-encoded image data.
*
* @format byte
*/
data: string;
/**
* The MIME type of the image. Different providers may support different image types.
*/
mimeType: string;
/**
* Optional annotations for the client.
*/
annotations?: Annotations;
}
/**
* Audio provided to or from an LLM.
*/
export interface AudioContent {
type: "audio";
/**
* The base64-encoded audio data.
*
* @format byte
*/
data: string;
/**
* The MIME type of the audio. Different providers may support different audio types.
*/
mimeType: string;
/**
* Optional annotations for the client.
*/
annotations?: Annotations;
}
/**
* The server's preferences for model selection, requested of the client during sampling.
*
* Because LLMs can vary along multiple dimensions, choosing the "best" model is
* rarely straightforward. Different models excel in different areas—some are
* faster but less capable, others are more capable but more expensive, and so
* on. This interface allows servers to express their priorities across multiple
* dimensions to help clients make an appropriate selection for their use case.
*
* These preferences are always advisory. The client MAY ignore them. It is also
* up to the client to decide how to interpret these preferences and how to
* balance them against other considerations.
*/
export interface ModelPreferences {
/**
* Optional hints to use for model selection.
*
* If multiple hints are specified, the client MUST evaluate them in order
* (such that the first match is taken).
*
* The client SHOULD prioritize these hints over the numeric priorities, but
* MAY still use the priorities to select from ambiguous matches.
*/
hints?: ModelHint[];
/**
* How much to prioritize cost when selecting a model. A value of 0 means cost
* is not important, while a value of 1 means cost is the most important
* factor.
*
* @TJS-type number
* @minimum 0
* @maximum 1
*/
costPriority?: number;
/**
* How much to prioritize sampling speed (latency) when selecting a model. A
* value of 0 means speed is not important, while a value of 1 means speed is
* the most important factor.
*
* @TJS-type number
* @minimum 0
* @maximum 1
*/
speedPriority?: number;
/**
* How much to prioritize intelligence and capabilities when selecting a
* model. A value of 0 means intelligence is not important, while a value of 1
* means intelligence is the most important factor.
*
* @TJS-type number
* @minimum 0
* @maximum 1
*/
intelligencePriority?: number;
}
/**
* Hints to use for model selection.
*
* Keys not declared here are currently left unspecified by the spec and are up
* to the client to interpret.
*/
export interface ModelHint {
/**
* A hint for a model name.
*
* The client SHOULD treat this as a substring of a model name; for example:
* - `claude-3-5-sonnet` should match `claude-3-5-sonnet-20241022`
* - `sonnet` should match `claude-3-5-sonnet-20241022`, `claude-3-sonnet-20240229`, etc.
* - `claude` should match any Claude model
*
* The client MAY also map the string to a different provider's model name or a different model family, as long as it fills a similar niche; for example:
* - `gemini-1.5-flash` could match `claude-3-haiku-20240307`
*/
name?: string;
}
/* Autocomplete */
/**
* A request from the client to the server, to ask for completion options.
*/
export interface CompleteRequest extends Request {
method: "completion/complete";
params: {
ref: PromptReference | ResourceReference;
/**
* The argument's information
*/
argument: {
/**
* The name of the argument
*/
name: string;
/**
* The value of the argument to use for completion matching.
*/
value: string;
};
};
}
/**
* The server's response to a completion/complete request
*/
export interface CompleteResult extends Result {
completion: {
/**
* An array of completion values. Must not exceed 100 items.
*/
values: string[];
/**
* The total number of completion options available. This can exceed the number of values actually sent in the response.
*/
total?: number;
/**
* Indicates whether there are additional completion options beyond those provided in the current response, even if the exact total is unknown.
*/
hasMore?: boolean;
};
}
/**
* A reference to a resource or resource template definition.
*/
export interface ResourceReference {
type: "ref/resource";
/**
* The URI or URI template of the resource.
*
* @format uri-template
*/
uri: string;
}
/**
* Identifies a prompt.
*/
export interface PromptReference {
type: "ref/prompt";
/**
* The name of the prompt or prompt template
*/
name: string;
}
/* Roots */
/**
* Sent from the server to request a list of root URIs from the client. Roots allow
* servers to ask for specific directories or files to operate on. A common example
* for roots is providing a set of repositories or directories a server should operate
* on.
*
* This request is typically used when the server needs to understand the file system
* structure or access specific locations that the client has permission to read from.
*/
export interface ListRootsRequest extends Request {
method: "roots/list";
}
/**
* The client's response to a roots/list request from the server.
* This result contains an array of Root objects, each representing a root directory
* or file that the server can operate on.
*/
export interface ListRootsResult extends Result {
roots: Root[];
}
/**
* Represents a root directory or file that the server can operate on.
*/
export interface Root {
/**
* The URI identifying the root. This *must* start with file:// for now.
* This restriction may be relaxed in future versions of the protocol to allow
* other URI schemes.
*
* @format uri
*/
uri: string;
/**
* An optional name for the root. This can be used to provide a human-readable
* identifier for the root, which may be useful for display purposes or for
* referencing the root in other parts of the application.
*/
name?: string;
}
/**
* A notification from the client to the server, informing it that the list of roots has changed.
* This notification should be sent whenever the client adds, removes, or modifies any root.
* The server should then request an updated list of roots using the ListRootsRequest.
*/
export interface RootsListChangedNotification extends Notification {
method: "notifications/roots/list_changed";
}
/* Client messages */
export type ClientRequest =
| PingRequest
| InitializeRequest
| CompleteRequest
| SetLevelRequest
| GetPromptRequest
| ListPromptsRequest
| ListResourcesRequest
| ReadResourceRequest
| SubscribeRequest
| UnsubscribeRequest
| CallToolRequest
| ListToolsRequest;
export type ClientNotification =
| CancelledNotification
| ProgressNotification
| InitializedNotification
| RootsListChangedNotification;
export type ClientResult = EmptyResult | CreateMessageResult | ListRootsResult;
/* Server messages */
export type ServerRequest =
| PingRequest
| CreateMessageRequest
| ListRootsRequest;
export type ServerNotification =
| CancelledNotification
| ProgressNotification
| LoggingMessageNotification
| ResourceUpdatedNotification
| ResourceListChangedNotification
| ToolListChangedNotification
| PromptListChangedNotification;
export type ServerResult =
| EmptyResult
| InitializeResult
| CompleteResult
| GetPromptResult
| ListPromptsResult
| ListResourcesResult
| ReadResourceResult
| CallToolResult
| ListToolsResult;
---
File: /scripts/validate_examples.ts
---
import * as fs from "fs";
import Ajv, { ValidateFunction } from "ajv";
import { globSync } from "glob";
import addFormats from "ajv-formats";
import { readFileSync } from "node:fs";
function createAjvInstance(): { ajv: Ajv; validate: ValidateFunction } {
const ajv = new Ajv({
// strict: true,
allowUnionTypes: true,
});
addFormats(ajv);
const schema = JSON.parse(readFileSync("schema/schema.json", "utf8"));
const validate = ajv.compile(schema);
return { ajv, validate };
}
function validateJsonBlocks(
validate: ValidateFunction,
filePath: string,
): void {
const content = fs.readFileSync(filePath, "utf8");
const jsonBlocks = content.match(/```json\s*\n([\s\S]*?)\n\s*```/g);
if (!jsonBlocks) {
console.log("No JSON blocks found in the file.");
return;
}
jsonBlocks.forEach((block, index) => {
try {
const jsonContent = block.replace(/```json\s*\n|\n\s*```/g, "");
const parsedJson = JSON.parse(jsonContent);
const valid = validate(parsedJson);
if (valid) {
console.log(`JSON block ${index + 1} is valid.`);
} else {
console.log(`JSON block ${index + 1} is invalid:`);
console.log(parsedJson);
console.log(validate.errors);
}
} catch (error) {
console.error(
`Error parsing JSON block ${index + 1}:`,
(error as Error).message,
);
}
});
}
const { validate } = createAjvInstance();
// Usage
const mdFiles = globSync("examples/**/*.md", {});
mdFiles.forEach((filePath) => {
console.log(`Validating JSON blocks in ${filePath}:`);
validateJsonBlocks(validate, filePath);
console.log("\n"); // Add a newline for separation between files
});
---
File: /site/layouts/index.html
---
Model Context Protocol Specification
Model Context Protocol Specification
Redirecting to specification ...
---
File: /README.md
---
# Model Context Protocol specification
This repo contains the specification and protocol schema for the Model Context Protocol.
The schema is [defined in TypeScript](schema/2024-11-05/schema.ts) first, but
[made available as JSON Schema](schema/2024-11-05/schema.json) as well, for wider
compatibility.
## Contributing
Please see [CONTRIBUTING.md](CONTRIBUTING.md) for details on how to contribute to this
project.
## License
This project is licensed under the MIT License—see the [LICENSE](LICENSE) file for
details.