home / mcp / biolink api mcp server

Biolink API MCP Server

Delivers an MCP server interface for the Biolink API, enabling clients to access Monarch Initiative data via Model Context Protocol.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "ag2-mcp-servers-biolink-api": {
      "command": "python",
      "args": [
        "mcp_server/main.py",
        "stdio"
      ],
      "env": {
        "CONFIG": "{\"transport\": \"stdio\"}.",
        "SECURITY": "API_KEY=YOUR_API_KEY",
        "CONFIG_PATH": "mcp_server/mcp_config.json"
      }
    }
  }
}

This MCP server exposes the Biolink API OpenAPI-based capabilities through the MCP protocol, enabling clients to query and interact with model-context data in a standardized way across environments.

How to use

You run the MCP server locally or in your environment and connect your MCP client to it using the defined MCP transport. Start the server in stdio mode and then direct your client to load the server via the standard MCP workflow. The server supports typical MCP client interactions for querying model-context operations and invoking actions exposed by the Biolink API surface.

How to install

Prerequisites include Python 3.9 or newer, plus pip and uv for running the server.

Install the project dependencies

pip install -e ".[dev]"
```

Alternatively, you can use uv to install dependencies in editable mode:
```
uv pip install --editable ".[dev]"

Clone and set up

Clone the MCP server repository and switch into the project directory.

Clone the repository

git clone <repository-url>
cd mcp-server

Run the server

Start the MCP server in stdio mode. This runs the server as a local process that communicates with MCP clients via standard input/output.

Start the server in stdio mode

python mcp_server/main.py stdio

Configure runtime options

You can customize how the server loads its configuration using environment variables.

Environment variables for runtime

The following environment variables control how the server loads its configuration and security settings.

Configuration options

- CONFIG_PATH: Path to a JSON configuration file (for example, mcp_server/mcp_config.json). - CONFIG: A JSON string containing the configuration. - SECURITY: Environment variables that define security parameters (for example, API keys).

Starting point example

python mcp_server/main.py stdio

Notes on testing and development

You can run tests, lint, and static analysis to ensure code quality during development. Use the provided scripts for linting, static analysis, and tests as part of your workflow.

Troubleshooting

If the server does not start, verify Python 3.9+ is installed, that you are in the correct project directory, and that dependencies were installed successfully. Check for environment variable typos and ensure the configuration file path or JSON string is valid.

Additional configuration and notes

The server is built to integrate with the Biolink API OpenAPI surface and provides MCP-based access to the context model. Ensure your MCP client is configured to communicate with the server via the stdio workflow or any other supported transport modes as implemented in the server.