Knowledgebase MCP

🚀 BioContextAI - Knowledgebase MCP

A Model Context Protocol (MCP) server for biomedical research that provides a standardized connection layer between artificial intelligence systems and biomedical resources.

🚀 Quick Start

BioContextAI Knowledgebase MCP is an MCP server implementation for common biomedical resources, enabling agentic large language models (LLMs) to retrieve verified information and perform domain - specific tasks. It offers a unified access layer via the Model Context Protocol for interoperability between AI systems and domain - specific data sources.

The Knowledgebase MCP is available in two forms:

• An open - source software package for local hosting (see Self - hosting).
• A remote server for setup - free integration at https://mcp.biocontext.ai/mcp/ (subject to fair use).

⚠️ Important Note

If possible, we encourage you to run BioContextAI Knowledgebase MCP locally to avoid rate limits and ensure the service's availability for applications that rely on remote hosting.

✨ Features

Implemented Tools

BioContextAI Knowledgebase MCP exposes a number of external biomedical APIs. You can think of BioContextAI as a browser for your LLM that allows it to find relevant information across these knowledge bases.

• Antibody Registry - Gene id conversion
• bioRxiv/medRxiv - Recent preprint search and metadata access
• Ensembl - Gene id conversion
• EuropePMC - Literature search and full - text access
• Google Scholar - Academic publication and author search (only available for local use due to rate limiting)
• InterPro - Protein families, domains, and functional sites classification
• KEGG - Pathways, gene and drug - drug interaction database (only available for local use due to licensing restrictions)
• OpenTargets - Target - disease associations
• PanglaoDB - Single - cell RNA - sequencing cell type markers
• PRIDE - Proteomics data repository for mass spectrometry data
• Protein Atlas - Protein expression data
• Reactome - Pathways database
• [STRING](https://string - db.org/) - Protein - protein interaction networks
• AlphaFold DB - Tertiary protein structure predictions

⚠️ Important Note

The data accessed through these APIs is not covered by the BioContextAI Knowledgebase MCP license. You are responsible for ensuring that your use of the data aligns with permitted practices. Also, please make sure to adhere to the usage limits (e.g., rate limits) of the respective services when using BioContextAI Knowledgebase MCP. If you use data from these services in your research, please make sure to cite both BioContextAI as well as the respective data source/tool.

OpenAPI MCP servers

FastMCP allows for easy conversion of REST endpoints following the OpenAPI specification into MCP servers. We have added code to automatically create such servers based on schemas provided through a configuration file, so that users deploying their own version of BioContextAI can easily extend the list of available tools. The configuration file is located at src/biocontext_kb/openapi/config.yaml. By default, no OpenAPI servers are included, but you can edit the configuration file to add services.

📦 Installation

Self - hosting

Clone the latest version of this repository:

git clone https://github.com/biocontext - ai/core - mcp - server.git
cd core - mcp - server

Then run one of the following:

1. Docker setup (gunicorn with multiple uvicorn workers):

# Build the docker container
docker build -t biocontext_kb:latest .
docker run -p 127.0.0.1:8000:8000 biocontext_kb:latest

This exposes your MCP server at: http://127.0.0.1:8000/mcp/

⚠️ Important Note

For public deployments, you should disabled unnecessary ports and access your MCP server through a reverse proxy, e.g., Nginx or Caddy. You may also want to configure the running user and the directory to have limited rights, use Docker or podman in a rootless setup and take additional security measures like DDOS protection with Cloudflare or fail2ban.

2. Local setup with uv, with streamable HTTP and uvicorn:

uv build
export MCP_ENVIRONMENT=PRODUCTION
export PORT=8000
biocontext_kb

3. Local setup with uv, with stdio transport:

uv build
export MCP_ENVIRONMENT=DEVELOPMENT
biocontext_kb

4. Local setup with Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "biocontext_kb": {
      "command": "uvx",
      "args": [
        "biocontext_kb@latest"
      ],
      "env": {
        "UV_PYTHON": "3.12"
      }
    }
  }
}

Don't forget to restart Claude to apply the changes.

5. Locally, with your coding agents in VS Code (.vscode/mcp.json) or Cursor (.cursor/mcp.json) or WindSurf (.codeium/windsurf/mcp_config.json):

{
  // VS Code: "servers"
  "mcpServers": {
    "biocontext_kb": {
      // if it doesn't work, replace with the `which uvx` path (installation via Homebrew recommended on macOS)
      "command": "uvx",
      "args": [
        "biocontext_kb@latest"
      ]
    }
  }
}

When using Windows and WSL2 the above config needs to be adapted as follows:

{
  // VS Code: "servers"
  "mcpServers": {
    "biocontext_kb": {
      "command": "wsl",
      "args": [
        "~/.local/bin/uvx", // set to the path to your `uvx`
        "biocontext_kb"
      ]
    }
  }
}

6. Locally, with your own MCP clients:

• Follow the PydanticAI setup guide.
• Follow the FastMCP [setup guide](https://gofastmcp.com/getting - started/welcome).
• Follow the mcp - use [setup guide](https://github.com/mcp - use/mcp - use).

📚 Documentation

• Project documentation: https://biocontext.ai
• API documentation: https://docs.kb.biocontext.ai/
• BioContextAI Registry: https://github.com/biocontext - ai/registry
• Chat Interface: https://biocontext.ai/chat

📄 License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

⚠️ Important Note

The Apache 2.0 License only applies to the code provided in this repository. For usage limitations and licenses of the individually integrated APIs, users should directly refer to the respective API providers. We provide an overview below.

Data Sources and Licensing

Disclaimer

Users are solely responsible for ensuring compliance with all applicable license terms and conditions when accessing data through this MCP server. The licenses and terms listed above are subject to change, and additional citation requirements may apply for specific datasets or publications. Before using any data for commercial purposes, redistribution, or publication, please review the current license terms directly from each data source. Some data sources may have additional restrictions not fully captured in this summary.

For KEGG data specifically, please note that while academic use is permitted, providing commercial services or remote hosting using KEGG data is not allowed under their proprietary license terms.

Citation

If our work is useful to your research, please cite it as below.

TBA.