Karol Fabjańczuk a69d8c91dc
feat: add configurable MCP tool loading to reduce LLM context usage (#1181)
Co-authored-by: Ralph Khreish <35776126+Crunchyman-ralph@users.noreply.github.com>
2025-10-14 20:01:21 +02:00

131 lines
4.3 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

---
title: Configuration
sidebarTitle: "Configuration"
---
Before getting started with Task Master, you'll need to set up your API keys. There are a couple of ways to do this depending on whether you're using the CLI or working inside MCP. It's also a good time to start getting familiar with the other configuration options available — even if you dont need to adjust them yet, knowing whats possible will help down the line.
## API Key Setup
Task Master uses environment variables to securely store provider API keys and optional endpoint URLs.
### MCP Usage: mcp.json file
For MCP/Cursor usage: Configure keys in the env section of your .cursor/mcp.json file.
```java .env lines icon="java"
{
"mcpServers": {
"task-master-ai": {
"command": "npx",
"args": ["-y", "task-master-ai"],
"env": {
"ANTHROPIC_API_KEY": "ANTHROPIC_API_KEY_HERE",
"PERPLEXITY_API_KEY": "PERPLEXITY_API_KEY_HERE",
"OPENAI_API_KEY": "OPENAI_API_KEY_HERE",
"GOOGLE_API_KEY": "GOOGLE_API_KEY_HERE",
"XAI_API_KEY": "XAI_API_KEY_HERE",
"OPENROUTER_API_KEY": "OPENROUTER_API_KEY_HERE",
"MISTRAL_API_KEY": "MISTRAL_API_KEY_HERE",
"AZURE_OPENAI_API_KEY": "AZURE_OPENAI_API_KEY_HERE",
"OLLAMA_API_KEY": "OLLAMA_API_KEY_HERE",
"GITHUB_API_KEY": "GITHUB_API_KEY_HERE"
}
}
}
}
```
<Tip>
**Optimize Context Usage**: You can control which Task Master MCP tools are loaded using the `TASK_MASTER_TOOLS` environment variable. This helps reduce LLM context usage by only loading the tools you need.
Options:
- `all` (default) - All 36 tools
- `standard` - 15 commonly used tools
- `core` or `lean` - 7 essential tools
Example:
```json
"env": {
"TASK_MASTER_TOOLS": "standard",
"ANTHROPIC_API_KEY": "your_key_here"
}
```
See the [MCP Tools documentation](/capabilities/mcp#configurable-tool-loading) for details.
</Tip>
### CLI Usage: `.env` File
Create a `.env` file in your project root and include the keys for the providers you plan to use:
```java .env lines icon="java"
# Required API keys for providers configured in .taskmaster/config.json
ANTHROPIC_API_KEY=sk-ant-api03-your-key-here
PERPLEXITY_API_KEY=pplx-your-key-here
# OPENAI_API_KEY=sk-your-key-here
# GOOGLE_API_KEY=AIzaSy...
# AZURE_OPENAI_API_KEY=your-azure-openai-api-key-here
# etc.
# Optional Endpoint Overrides
# Use a specific provider's base URL, e.g., for an OpenAI-compatible API
# OPENAI_BASE_URL=https://api.third-party.com/v1
#
# Azure OpenAI Configuration
# AZURE_OPENAI_ENDPOINT=https://your-resource-name.openai.azure.com/ or https://your-endpoint-name.cognitiveservices.azure.com/openai/deployments
# OLLAMA_BASE_URL=http://custom-ollama-host:11434/api
# Google Vertex AI Configuration (Required if using 'vertex' provider)
# VERTEX_PROJECT_ID=your-gcp-project-id
```
## What Else Can Be Configured?
The main configuration file (`.taskmaster/config.json`) allows you to control nearly every aspect of Task Masters behavior. Heres a high-level look at what you can customize:
<Tip>
You dont need to configure everything up front. Most settings can be left as defaults or updated later as your workflow evolves.
</Tip>
<Accordion title="View Configuration Options">
### Models and Providers
- Role-based model setup: `main`, `research`, `fallback`
- Provider selection (Anthropic, OpenAI, Perplexity, etc.)
- Model IDs per role
- Temperature, max tokens, and other generation settings
- Custom base URLs for OpenAI-compatible APIs
### Global Settings
- `logLevel`: Logging verbosity
- `debug`: Enable/disable debug mode
- `projectName`: Optional name for your project
- `defaultTag`: Default tag for task grouping
- `defaultSubtasks`: Number of subtasks to auto-generate
- `defaultPriority`: Priority level for new tasks
### API Endpoint Overrides
- `ollamaBaseURL`: Custom Ollama server URL
- `azureBaseURL`: Global Azure endpoint
- `vertexProjectId`: Google Vertex AI project ID
- `vertexLocation`: Region for Vertex AI models
### Tag and Git Integration
- Default tag context per project
- Support for task isolation by tag
- Manual tag creation from Git branches
### State Management
- Active tag tracking
- Migration state
- Last tag switch timestamp
</Accordion>
<Note>
For advanced configuration options and detailed customization, see our [Advanced Configuration Guide](/best-practices/configuration-advanced) page.
</Note>