Skip to main content

A collection of Model Context Protocol (MCP) servers for biomedical research, providing AI assistants with access to various biomedical databases and resources

Project description

Biomedical public MCP Servers

This is not Gosset MCP as described here. For accessing Gosset MCP you need an active Gosset account. Reach out to us for details.

A collection of Model Context Protocol (MCP) servers for biomedical research, providing AI assistants with access to various biomedical databases and resources.

What is MCP?

The Model Context Protocol (MCP) allows AI assistants like Claude to access external tools and data sources. These servers extend Claude's capabilities by providing access to specific biomedical databases.

Available Servers

This repository contains the following MCP servers:

PubMed MCP Server

Access the PubMed database of biomedical literature.

  • Search PubMed for articles matching a query
  • Retrieve abstracts for specific articles
  • Find related articles based on a PMID
  • Search for articles by a specific author

BioRxiv/MedRxiv MCP Server

Access preprints from bioRxiv and medRxiv repositories.

  • Get detailed information about preprints by DOI
  • Find published versions of preprints
  • Search for recent preprints
  • Search preprints by date range and category

ClinicalTrials.gov MCP Server

Access information about clinical trials.

  • Search for trials matching specific criteria
  • Get detailed information about specific trials
  • Find trials by medical condition
  • Find trials by location

DrugBank MCP Server

Access drug information from DrugBank.

  • Search for drugs by name
  • Get detailed information about specific drugs
  • Find drugs by indication
  • Find drugs by category
  • Get drug interaction information

OpenTargets MCP Server

Access drug target information from Open Targets.

  • Search for gene targets
  • Get detailed target information
  • Search for diseases
  • Find disease-target associations
  • Search for drugs

Setup

  1. Install dependencies for all servers:

    pip install -r requirements.txt
    
  2. For specific servers, additional setup may be required:

    • For PubMed: Update the EMAIL constant in pubmed_mcp.py with your email address (required by NCBI)
    • For DrugBank: Add your DrugBank API key to the API_KEY constant in drugbank_mcp.py
  3. Run a server:

    python pubmed_mcp.py  # Replace with the server you want to run
    

Connecting to Claude for Desktop

To use these servers with Claude for Desktop:

  1. Make sure you have the latest version of Claude for Desktop installed.

  2. Edit your Claude for Desktop configuration file located at:

    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Windows: %AppData%\Claude\claude_desktop_config.json
  3. Add server configurations:

    {
        "mcpServers": {
            "pubmed-mcp": {
                "command": "python",
                "args": [
                    "/ABSOLUTE/PATH/TO/pubmed_mcp.py"
                ]
            },
            "biorxiv-mcp": {
                "command": "python",
                "args": [
                    "/ABSOLUTE/PATH/TO/bioarxiv_mcp.py"
                ]
            },
            "clinicaltrials-mcp": {
                "command": "python",
                "args": [
                    "/ABSOLUTE/PATH/TO/clinicaltrialsgov_mcp.py"
                ]
            },
            "drugbank-mcp": {
                "command": "python",
                "args": [
                    "/ABSOLUTE/PATH/TO/drugbank_mcp.py"
                ]
            },
            "opentargets-mcp": {
                "command": "python",
                "args": [
                    "/ABSOLUTE/PATH/TO/opentargets_mcp.py"
                ]
            }
        }
    }
    

    Replace /ABSOLUTE/PATH/TO/ with the absolute path to each script on your system.

  4. Restart Claude for Desktop.

Example Queries

  • "Find recent research on CRISPR therapy for cancer"
  • "Get me the abstract for PMID 34567890"
  • "What preprints were published last week on COVID-19?"
  • "What clinical trials are currently recruiting for Alzheimer's disease?"
  • "Find information about the drug metformin"
  • "What targets are associated with Parkinson's disease?"

Troubleshooting

If you encounter issues:

  1. Check that you've properly configured the server
  2. Make sure you've restarted Claude for Desktop after updating the configuration
  3. Check Claude's logs for errors:
    • macOS: ~/Library/Logs/Claude/mcp*.log
    • Windows: %APPDATA%\Claude\logs\mcp*.log

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

File details

Details for the file iflow_mcp_kidzik_biomedical_public_mcps-0.1.0.tar.gz.

File metadata

  • Download URL: iflow_mcp_kidzik_biomedical_public_mcps-0.1.0.tar.gz
  • Upload date:
  • Size: 12.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.0 {"installer":{"name":"uv","version":"0.10.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for iflow_mcp_kidzik_biomedical_public_mcps-0.1.0.tar.gz
Algorithm Hash digest
SHA256 2554e431140d3ab2a6a5477a754c439d669edd91fa2f29fc182563e49d005ee7
MD5 b2fa6e556cdfd64e3cf97f6b1828cacb
BLAKE2b-256 7f39660c5b5d168544388d60fe8d2b9d04d03c3483069e4b3c0867380b9cf277

See more details on using hashes here.

File details

Details for the file iflow_mcp_kidzik_biomedical_public_mcps-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: iflow_mcp_kidzik_biomedical_public_mcps-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 27.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.10.0 {"installer":{"name":"uv","version":"0.10.0","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for iflow_mcp_kidzik_biomedical_public_mcps-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 3ffb2c350b49c9d6776dd7818eeebbaa4528274252654b918ea82c92c34b4d08
MD5 9bf92c496ca045d36e61babe01d47a70
BLAKE2b-256 0f86a338e748e65f9af663f672fdfa47ff32f8d29d92dc3844de02ee41e91f44

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page