Open Targets MCP server

Integrates with Open Targets platform to search therapeutic targets and diseases, retrieve detailed gene and disease information, and analyze target-disease associations with evidence scores for drug discovery and biomedical research.
Back to servers
Setup instructions
Provider
Augmented Nature
Release date
Jun 01, 2025
Language
Go
Stats
6 stars

The Unofficial Open Targets MCP Server provides a Model Context Protocol server for accessing Open Targets platform data, allowing researchers to explore gene-drug-disease associations through standardized tools and queries.

Installation

To install and run the Open Targets MCP server:

# Install and build
npm install
npm run build

# Run the server
node build/index.js

Client Configuration

Claude Desktop Configuration

{
  "mcpServers": {
    "opentargets-server": {
      "command": "node",
      "args": ["/path/to/opentargets-server/build/index.js"]
    }
  }
}

Other MCP Clients

For other clients, simply run the server directly:

node /path/to/opentargets-server/build/index.js

Available Tools

The server provides six specialized tools for accessing Open Targets data:

Target Search

Search for therapeutic targets by gene symbol, name, or description:

{
  "name": "search_targets",
  "arguments": {
    "query": "BRCA1",
    "size": 10
  }
}

Example results include:

  • BRCA1 (ENSG00000012048) - BRCA1 DNA repair associated
  • BRCA2 (ENSG00000139618) - BRCA2 DNA repair associated
  • BRIP1 (ENSG00000136492) - BRCA1 interacting DNA helicase 1

Disease Search

Search diseases by name, synonym, or description:

{
  "name": "search_diseases",
  "arguments": {
    "query": "breast cancer",
    "size": 10
  }
}

Target-Disease Associations

Get associations between targets and diseases with evidence scores:

{
  "name": "get_target_disease_associations",
  "arguments": {
    "targetId": "ENSG00000012048",
    "size": 10
  }
}

Or search by disease:

{
  "name": "get_target_disease_associations",
  "arguments": {
    "diseaseId": "EFO_0000305",
    "size": 10
  }
}

Disease Targets Summary

Get prioritized targets associated with a specific disease:

{
  "name": "get_disease_targets_summary",
  "arguments": {
    "diseaseId": "EFO_0000305",
    "size": 20
  }
}

Target Details

Get comprehensive information about a specific target:

{
  "name": "get_target_details",
  "arguments": {
    "id": "ENSG00000012048"
  }
}

Disease Details

Get comprehensive information about a specific disease:

{
  "name": "get_disease_details",
  "arguments": {
    "id": "EFO_0000305"
  }
}

Resource Templates

Access Open Targets data through standardized URIs:

  • opentargets://target/{ensemblId} - Complete target information
  • opentargets://disease/{efoId} - Complete disease information
  • opentargets://drug/{chemblId} - Drug information
  • opentargets://association/{targetId}/{diseaseId} - Association evidence
  • opentargets://search/{query} - Search results

Example Workflows

Cancer Research Workflow

# 1. Search for cancer-related targets
{"name": "search_targets", "arguments": {"query": "oncogene", "size": 10}}

# 2. Get detailed info for specific target
{"name": "get_target_details", "arguments": {"id": "ENSG00000012048"}}

# 3. Find all diseases associated with BRCA1
{"name": "get_target_disease_associations", "arguments": {"targetId": "ENSG00000012048"}}

# 4. Get top targets for breast cancer
{"name": "get_disease_targets_summary", "arguments": {"diseaseId": "EFO_0000305", "size": 20}}

Drug Discovery Pipeline

# 1. Search for Alzheimer's disease
{"name": "search_diseases", "arguments": {"query": "Alzheimer", "size": 5}}

# 2. Get disease details
{"name": "get_disease_details", "arguments": {"id": "EFO_0000249"}}

# 3. Find prioritized therapeutic targets
{"name": "get_disease_targets_summary", "arguments": {"diseaseId": "EFO_0000249", "size": 30}}

Data Sources

The Open Targets platform integrates data from over 20 databases including:

  • ChEMBL - Drug & compound data
  • Ensembl - Gene & protein annotations
  • EFO - Experimental Factor Ontology
  • ClinVar - Clinical variant data
  • GWAS Catalog - Genome-wide association studies
  • UniProt - Protein sequences & functions
  • Reactome - Biological pathways

The system uses standardized identifiers:

  • Targets: Ensembl gene IDs (e.g., ENSG00000012048)
  • Diseases: EFO IDs (e.g., EFO_0000305)
  • Drugs: ChEMBL IDs (e.g., CHEMBL1234)

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "opentargets-server" '{"command":"node","args":["/path/to/opentargets-server/build/index.js"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "opentargets-server": {
            "command": "node",
            "args": [
                "/path/to/opentargets-server/build/index.js"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "opentargets-server": {
            "command": "node",
            "args": [
                "/path/to/opentargets-server/build/index.js"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later