yujunjun/datahub
2
0
Fork 0
mirror of https://github.com/datahub-project/datahub.git synced 2025-10-31 18:59:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs(mcp): prefer the latest MCP server (#14077)

Browse Source
This commit is contained in:
Harshal Sheth 2025-07-16 05:23:00 -07:00 committed by GitHub
parent b1c3d33235
commit 7d2df4a63b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
docs/features/feature-guides/mcp.md
View File

@ -36,9 +36,9 @@ The managed MCP server endpoint is only available with DataHub Cloud v0.3.12+. F
::: :::
:::note :::note Streamable HTTP Only
There are two [transports types](https://modelcontextprotocol.io/docs/concepts/transports) for remote MCP servers: streamable HTTP and server-sent events (SSE). DataHub only supports the newer streamable HTTP transport. SSE has been deprecated in favor of streamable HTTP, but some older MCP clients may still only support SSE. For those cases, you'll need to use something like [mcp-remote](https://github.com/geelen/mcp-remote) to bridge the gap. There are two [transports types](https://modelcontextprotocol.io/docs/concepts/transports) for remote MCP servers: streamable HTTP and server-sent events (SSE). SSE has been deprecated in favor of streamable HTTP, so DataHub only supports the newer streamable HTTP transport. Some older MCP clients (e.g. chatgpt.com) may still only support SSE. For those cases, you'll need to use something like [mcp-remote](https://github.com/geelen/mcp-remote) to bridge the gap.
::: :::
@ -145,7 +145,7 @@ You can run the [open-source MCP server](https://github.com/acryldata/mcp-server
"mcpServers": { "mcpServers": {
"datahub": { "datahub": {
"command": "<full-path-to-uvx>", // e.g. /Users/hsheth/.local/bin/uvx "command": "<full-path-to-uvx>", // e.g. /Users/hsheth/.local/bin/uvx
"args": ["mcp-server-datahub"], "args": ["mcp-server-datahub@latest"],
"env": { "env": {
"DATAHUB_GMS_URL": "<your-datahub-url>", "DATAHUB_GMS_URL": "<your-datahub-url>",
"DATAHUB_GMS_TOKEN": "<your-datahub-token>" "DATAHUB_GMS_TOKEN": "<your-datahub-token>"
@ -168,7 +168,7 @@ You can run the [open-source MCP server](https://github.com/acryldata/mcp-server
"mcpServers": { "mcpServers": {
"datahub": { "datahub": {
"command": "uvx", "command": "uvx",
"args": ["mcp-server-datahub"], "args": ["mcp-server-datahub@latest"],
"env": { "env": {
"DATAHUB_GMS_URL": "<your-datahub-url>", "DATAHUB_GMS_URL": "<your-datahub-url>",
"DATAHUB_GMS_TOKEN": "<your-datahub-token>" "DATAHUB_GMS_TOKEN": "<your-datahub-token>"
@ -188,7 +188,7 @@ You can run the [open-source MCP server](https://github.com/acryldata/mcp-server
For other AI tools, you'll typically need to provide the following configuration: For other AI tools, you'll typically need to provide the following configuration:
- Command: `uvx` - Command: `uvx`
- Args: `mcp-server-datahub` - Args: `mcp-server-datahub@latest`
- Env: - Env:
- `DATAHUB_GMS_URL`: `<your-datahub-url>` - `DATAHUB_GMS_URL`: `<your-datahub-url>`
- `DATAHUB_GMS_TOKEN`: `<your-datahub-token>` - `DATAHUB_GMS_TOKEN`: `<your-datahub-token>`