STRING

Provides access to STRING protein interaction data and analysis tools via MCP endpoints.

typescript

0

GitHub Stars

typescript

Language

5 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": {
    "munch-group-string-mcp": {
      "command": "node",
      "args": [
        "/path/to/string-mcp/build/index.js"
      ]
    }
  }
}

The STRING MCP Server provides programmatic access to the STRING protein-protein interaction database and a set of analysis tools that you can use from MCP-enabled clients. It enables tasks such as mapping identifiers, retrieving networks, identifying partners, and performing functional enrichment analyses, all through MCP endpoints or local runtime configurations.

How to use

You can connect to the STRING MCP Server from an MCP client either by running the server locally via a stdio command or by invoking it through a package runner. Use the local node-based runtime to load the built server, or use npx to run the MCP package on demand. The server exposes a suite of protein interaction analysis tools you can invoke as needed without writing your own integration.

How to install

# Prerequisites
- Node.js (recommended current LTS)
- npm (comes with Node.js)

# Install from GitHub and build the project
npm install git+https://github.com/munch-group/string-mcp.git
cd node_modules/string-mcp
npm run build

# Or install from source and build
git clone https://github.com/munch-group/string-mcp.git
cd string-mcp
npm install
npm run build

Configuration

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

Troubleshooting and notes

If you encounter issues starting the server, ensure you have built the project successfully and that the path to the built index.js is correct. For runtime environments, verify that your MCP client can locate the declared command and arguments and that there are no permission errors when launching the process.

Available tools

Mapping protein identifiers

Maps input protein identifiers to STRING IDs to align data across datasets.

Retrieving protein interaction networks

Fetches interaction networks for target proteins to visualize relationships.

Finding interaction partners

Identifies proteins that interact with a given protein of interest.

Functional enrichment analysis

Performs GO, KEGG, and pathway enrichment analyses on protein sets.

PPI enrichment testing

Assesses the significance of observed protein-protein interaction networks.

Cross-species homology mapping

Maps proteins across species to enable comparative analyses.

Protein name resolution

Resolves protein names and aliases to standardized identifiers.