agentience tribal mcp server

WHAT IT CONNECTS

agentience tribal mcp server 为 AI Agent 提供什么

• Store and retrieve error records with full context
• Vector similarity search using ChromaDB
• REST API (FastAPI) and native MCP interfaces
• JWT authentication with API keys
• Local storage (ChromaDB) and AWS integration
• Docker-compose deployment
• CLI client integration
• Store programming errors and solutions
• Search for similar errors when you encounter problems
• Build a knowledge base specific to your coding patterns
• Python 3.12+
• uv package manager (recommended)
• `add_error` - Create new error record (POST /errors)
• `get_error` - Retrieve error by UUID (GET /errors/{id})
• `update_error` - Modify existing error (PUT /errors/{id})
• `delete_error` - Remove error record (DELETE /errors/{id})
• `search_errors` - Find errors by criteria (GET /errors)
• `find_similar` - Semantic similarity search (GET /errors/similar)
• `get_token` - Obtain JWT token (POST /token)
• "Look for similar errors in our Tribal knowledge base"
• "Store this solution to our error database"
• "Check if we've seen this error before"
• `PERSIST_DIRECTORY`: ChromaDB storage path (default: "./chroma_db")
• `API_KEY`: Authentication key (default: "dev-api-key")
• `SECRET_KEY`: JWT signing key (default: "insecure-dev-key-change-in-production")
• `REQUIRE_AUTH`: Authentication requirement (default: "false")
• `PORT`: Server port (default: 8000)
• `MCP_API_URL`: FastAPI server URL (default: "http://localhost:8000")
• `MCP_PORT`: MCP server port (default: 5000)
• `MCP_HOST`: Host to bind to (default: "0.0.0.0")
• `API_KEY`: FastAPI access key (default: "dev-api-key")
• `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, `AWS_S3_BUCKET`: For AWS integration
• `POST /errors`: Create new error record
• `GET /errors/{error_id}`: Get error by ID
• `PUT /errors/{error_id}`: Update error record
• `DELETE /errors/{error_id}`: Delete error
• `GET /errors`: Search errors by criteria
• `GET /errors/similar`: Find similar errors
• `POST /token`: Get authentication token
• Tribal uses ChromaDB to store error records and solutions
• When Claude encounters an error, it sends the error details to Tribal
• Tribal vectorizes the error and searches for similar ones
• Claude gets back relevant solutions to suggest
• New solutions are stored for future reference
• **Test**: Runs linting, type checking, and unit tests
• Uses Python 3.12
• Installs dependencies with uv
• Runs ruff, black, mypy, and pytest
• **Build and Publish**: Builds and publishes the package to PyPI
• Triggered only on push to main branch
• Uses Python's build system
• Publishes to PyPI using twine
• Checks Python version (3.12 recommended)
• Installs dependencies using uv
• Runs linting with ruff
• Checks formatting with black
• Runs type checking with mypy
• Runs tests with pytest
• Builds the package
• Version numbering (MAJOR.MINOR.PATCH)
• Schema versioning for database compatibility
• Branch naming conventions
• Release and hotfix procedures
• Open `~/Library/Application Support/Claude/claude_desktop_config.json`
• Add the MCP server configuration (assumes Tribal tool is already installed):
• Restart Claude for Desktop
• Start the container:
• Configure Claude for Desktop:
• Verify Tribal installation: `which tribal`
• Check configuration: `claude mcp list`
• Test server status: `tribal status`
• Look for error messages in the Claude output
• Check the database directory exists and has proper permissions
• `S3Storage`: For storing error records in Amazon S3
• `DynamoDBStorage`: For using DynamoDB as the database