STRING

A comprehensive Model Context Protocol (MCP) server for accessing the STRING protein interaction database. This server provides powerful tools for protein network analysis, functional enrichment, and comparative genomics through the STRING API.

javascript

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "augmented-nature-string-db-mcp-server": {
      "command": "node",
      "args": [
        "/path/to/string-server/build/index.js"
      ]
    }
  }
}

You can run a dedicated MCP server to access the STRING protein interaction database, enabling direct protein interaction queries, network analysis, functional enrichment, and cross-species comparisons within your workflow. This MCP server exposes a set of tools that connect to the STRING API and lets you build and analyze protein networks directly from your environment.

How to use

Once you have the MCP server running, you can connect to it from your MCP client and invoke tools to fetch interactions, build networks, perform enrichment analyses, and locate homologs. Use the available tools by referencing their names (below) in your client calls, and treat the server as a standard MCP endpoint that returns structured results for each operation.

How to install

# Install dependencies
npm install

# Build the server
npm run build

# Run in development mode
npm run dev

After the server is running, you can add it to your client configuration to enable local execution. The following config integrates the STRING MCP server as a local process that your client can start and manage.

Configuration for a client

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

Notes

Prerequisites include having Node.js and npm available on your system. Use the npm-driven workflow to install, build, and run the server in development mode, then connect your MCP client using the provided configuration snippet.

Available tools

get_protein_interactions

Fetch direct interaction partners for a given protein, including confidence scores and evidence types.

get_interaction_network

Build and analyze protein interaction networks for a set of proteins, enabling network-level insights.

get_functional_enrichment

Run functional enrichment analyses using GO terms, KEGG pathways, and other annotations for a protein set.

get_protein_annotations

Retrieve detailed protein annotations and functional information for specified proteins.

find_homologs

Identify homologous proteins across species to support comparative analyses.

search_proteins

Search for proteins by name or identifier across multiple species.

Built by

VeilStrat

AI signals for GTM teams