The Open Targets MCP Server exposes the Open Targets Platform GraphQL API as a set of tools for use with MCP-compatible clients, enabling various biomedical data analyses.
From the registry: Open Targets MCP server for targets, diseases, drugs, variants, and evidence

Please install the `opentargets` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Python 3.10+** — Required to run the server (https://www.python.org/)
- **uv** — Python package manager used to run the server Run: `pip install uv` (https://github.com/astral-sh/uv)
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["--from","git+https://github.com/nickzren/opentargets-mcp","opentargets-mcp"]
- optional environment variables:
- `OPEN_TARGETS_API_URL`: Open Targets GraphQL API endpoint (example: `https://api.platform.opentargets.org/api/v4/graphql`)
- `MCP_TRANSPORT`: Transport mode: stdio, sse, or http (example: `stdio`)
Note: No API key required — accesses the public Open Targets Platform GraphQL API. 68 tools for biomedical data. Supports stdio/SSE/HTTP transports.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.OPEN_TARGETS_API_URLrequiredAPI endpoint for the Open Targets Platform.OPEN_TARGETS_RATE_LIMIT_RPSRate limit for requests per second.OPEN_TARGETS_RATE_LIMIT_BURSTBurst rate limit for requests.MCP_TRANSPORTTransport protocol used by the server.FASTMCP_SERVER_HOSTHost address for the MCP server.FASTMCP_SERVER_PORTPort number for the MCP server.