Reactome
Model Context Protocol server for accessing Reactome pathway and systems biology data.
claude mcp add --transport stdio augmented-nature-reactome-mcp-server node /path/to/reactome-server/build/index.js
How to use
The Unofficial Reactome MCP Server exposes a set of MCP-compliant tools backed by the Reactome REST API. It provides capabilities to search for biological pathways, retrieve detailed pathway information, discover pathways by gene across species, explore disease-associated pathways, examine pathway hierarchies, list pathway participants, fetch biochemical reactions, and inspect protein interactions within pathways. Clients communicate using the MCP JSON-RPC structure described in the documentation, issuing named commands like search_pathways, get_pathway_details, find_pathways_by_gene, find_pathways_by_disease, get_pathway_hierarchy, get_pathway_participants, get_pathway_reactions, and get_protein_interactions. Real-world workflows often combine multiple tools to build a complete picture of a pathway or mechanism, from high-level pathway search to granular reaction and participant details.
To use the server, start it via your MCP client configuration, for example by running the built server file with Node.js as shown in the quick start. From a client, you can issue a request for a pathway by ID to fetch comprehensive details, or search for pathways by a gene like BRCA1 to identify related pathways. The client examples in the README demonstrate how to structure the JSON payloads for each tool and how to interpret the returned results.
How to install
Prerequisites:
- Node.js and npm installed on your system
- Internet access to install dependencies
- Clone the repository or obtain the MCP server package from your source control.
- Navigate to the project directory.
- Install dependencies: npm install
- Build the server (if a build step is required by the project): npm run build
- Run the server (development mode): node build/index.js
- Configure your MCP clients to point to the server process (see mcp_config for example).
Notes:
- Ensure the Reactome API is reachable from the server host (the base URL is typically the Reactome Content Service endpoint).
- If building produces a different output path, adjust the mcp_config accordingly.
Additional notes
Tips and tips:
- No authentication is required for the Reactome data access in this MCP server, but check any environment-specific network restrictions.
- If you run into timeouts or API rate limits, consider adjusting client-side timeouts or adding caching at the client layer.
- Environment variables you might encounter include API_BASE_URL (Reactome REST endpoint), and optional API keys if you apply access control in certain deployments. The README indicates that the MCP server itself leverages the Reactome Content Service API; verify any external API changes or version updates (e.g., v79) and adjust queries accordingly.
- Common issues: incorrect build path in mcp_config, network restrictions preventing outgoing requests to Reactome, and mismatched JSON-RPC request formats between client and server. Validate requests against the examples in the README to ensure proper structure.
Related MCP Servers
zen
Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage
MCP -Deepseek_R1
A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)
mcp-fhir
A Model Context Protocol implementation for FHIR
mcp
Inkdrop Model Context Protocol Server
mcp-appium-gestures
This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..
dubco -npm
The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.