Suggested as an alternative reverse proxy for accessing the MCP server in public deployments.
Mentioned as a recommended security measure for public deployments, providing DDOS protection for the MCP server.
Provides containerization for the MCP server with gunicorn and multiple uvicorn workers, offering a deployment option with isolation.
Integration with GitHub CI workflows for continuous integration, as indicated by the badge in the README.
Enables academic publication and author search with Google Scholar's database, though only available for local use due to rate limiting.
Recommended as a reverse proxy option for accessing the MCP server in public deployments to enhance security.
Mentioned as an alternative to Docker for rootless setup in secure deployments of the MCP server.
A Model Context Protocol (MCP) server for biomedical research that provides a standardized connection layer between artificial intelligence systems and biomedical resources. Documentation and usage guides are available at: https://biocontext.ai
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. Unlike previous approaches that required custom integration for each resource, BioContextAI KB MCP provides a unified access layer through the Model Context Protocol that enables interoperability between AI systems and domain-specific data sources.
The Knowledgebase MCP is available both as:
Warning
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.
The Knowledgebase MCP is part of the wider BioContextAI project. The BioContextAI Registry catalogues community servers that expose biomedical databases and analysis tools, providing the community with a resource for tool discovery and distribution. The registry index can be found at: https://biocontext.ai/registry.
If our work is useful to your research, please cite it as below.
TBA.
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. 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.
Warning
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.
The above data is provided without warranty and may be inaccurate or out-of-date. Please verify your use case is allowed.
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.
Clone the latest version of this repository:
Then run one of the following:
This exposes your MCP server at: http://127.0.0.1:8000/mcp/
Warning
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.
uv, with streamable HTTP and uvicorn:uv, with stdio transport:claude_desktop_config.json):Don't forget to restart Claude to apply the changes.
.vscode/mcp.json) or Cursor (.cursor/mcp.json) or WindSurf (.codeium/windsurf/mcp_config.json):When using Windows and WSL2 the above config needs to be adapted as follows:
PydanticAI setup guideFastMCP setup guidemcp-use setup guideThis project is licensed under the Apache License 2.0 - see the LICENSE file for details.
Warning
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 Source | License | URL | Notes |
|---|---|---|---|
| AlphaFold (EMBL-EBI) | CC BY 4.0 | https://alphafold.ebi.ac.uk/ | |
| Antibody Registry (RRIDs) | CC0 (metadata: CC-NC) | https://www.antibodyregistry.org/faq | Commercial reuse restrictions on some metadata |
| bioRxiv/medRxiv | CC BY 4.0 | https://www.biorxiv.org/about/FAQ | Preprint content licenses vary |
| ClinicalTrials.gov API | Terms of Service | https://clinicaltrials.gov/about-site/terms-conditions | Attribution required |
| Ensembl | No restrictions* | https://www.ensembl.org/info/about/legal/disclaimer.html | *Some third-party data may have restrictions |
| EuropePMC | Various/Copyright protected | https://europepmc.org/Copyright | Individual article licenses vary |
| Google Scholar | Terms of Service | https://scholar.google.com/intl/en/scholar/terms.html | Rate limiting; use responsibly |
| Grants.gov API | Terms of Service | https://www.grants.gov/api/terms-conditions | Attribution required |
| Human Protein Atlas | CC BY-SA 4.0 | https://www.proteinatlas.org/about/licence | |
| InterPro | CC0 1.0 Universal | https://www.ebi.ac.uk/interpro/ | Includes InterPro, Pfam, PRINTS, and SFLD data |
| KEGG | Proprietary (Free academic use) | https://www.kegg.jp/kegg/legal.html | Commercial services/remote hosting not permitted |
| Ontology Lookup Service (EMBL-EBI) | Generally CC0/CC BY | https://www.ebi.ac.uk/licencing/ | Refer to EMBL-EBI general licensing |
| Open Targets | CC0 1.0 | https://platform-docs.opentargets.org/licence | |
| OpenFDA | CC0 1.0 Universal* | https://open.fda.gov/license/ | *Some data may have restrictions |
| PanglaoDB | Public data | https://panglaodb.se/about.html | All data are public |
| PRIDE | CC0/CC BY 4.0* | https://www.ebi.ac.uk/pride/markdownpage/license | *CC0 for datasets from June 2018+, CC BY 4.0 for derived resources |
| Reactome | CC0 | https://reactome.org/license | |
| STRING | CC BY 4.0 | https://string-db.org/cgi/access?footer_active_subpage=licensing | |
| UniProt | CC BY 4.0 | https://www.uniprot.org/help/license |
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.
This server cannot be installed
An MCP server that provides standardized access to biomedical knowledge bases and resources, enabling AI systems to retrieve verified information from sources like bioRxiv, EuropePMC, and various protein/gene databases.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/biocontext-ai/knowledgebase-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server