
Minds
STDIOMCP server enabling LLM interaction with Minds SDK for AI completions
MCP server enabling LLM interaction with Minds SDK for AI completions
An MCP (Model Context Protocol) server for Minds, allowing LLMs to interact with the Minds SDK through a standardized interface.
Install the required dependencies (virtual environment recommended)
python -m venv env source env/bin/activate
pip install -r requirements.txt pip install -r requirements-dev.txt
The server can be configured using environment variables:
FASTMCP_DEBUG
: Enable debug mode (default: false)FASTMCP_LOG_LEVEL
: Set log level (default: INFO)FASTMCP_HOST
: Host to bind to (default: 0.0.0.0)FASTMCP_PORT
: Port to bind to (default: 8000)FASTMCP_SSE_PATH
: Path for SSE events (default: /sse)FASTMCP_MESSAGE_PATH
: Path for messages (default: /messages/)MINDS_BASE_URL
: Base URL for the Minds API (default: https://mdb.ai)python -m server
The server exposes the following resource templates according to the MCP specification:
minds://{api_key}
- List all available Mindsminds://{mind_name}/{api_key}
- Get a specific Mind by nameThe server provides the following tool templates:
completion
- Generate a completion using a specified Mind
mind_name
: The ID of the Mind to usemessage
: The message to completeapi_key
: The Minds API key# Run all tests python -m pytest # Run only unit tests python -m pytest tests/unit
For easier development, you can use the MCP development server:
mcp dev server.py
This will start the server and open the MCP Inspector in your browser for testing.
This server implements the Model Context Protocol (MCP), which provides:
MCP clients can: