STRING

STRING-MCP provides a Python-based bridge that lets MCP-compatible clients interact with the STRING database API. It exposes a server and a set of tools to map identifiers, retrieve networks, perform enrichment analyses, visualize networks, and access STRING version information, all through the MCP protocol. This makes it easy to integrate STRING data into automated workflows and multi-tool analyses.

How to use

You run the MCP server locally and connect your MCP client to it. The server exposes a set of tools that you can invoke from your client to perform protein identifier mapping, retrieve protein interaction networks, run functional enrichment, generate network visuals, and query version information. Use the client to discover tools, pass your protein lists, specify species, and handle results in JSON, TSV, XML, or image formats.

How to install

Prerequisites: make sure you have Python installed (3.8 or newer) and a supported runtime for your environment.

# Create and activate a virtual environment (recommended)
python -m venv venv
source venv/bin/activate  # On Windows use: venv\Scripts\activate

# Install in development mode (if you are actively developing)
pip install -e .

# Or install from PyPI when available
pip install string-mcp

Configuration and usage notes

Configure the MCP server in your client by pointing to the MCP endpoint and ensuring the server is started with the expected command. The following example shows a local stdio server configuration that starts the MCP server using the provided command.

{
  "mcpServers": {
    "string_mcp": {
      "type": "stdio",
      "command": "string-mcp-server",
      "args": [],
      "env": {}
    }
  }
}

Examples of common workflows

Initialize the bridge in your client and call the available methods to map identifiers, fetch networks, and perform enrichment. You can request outputs in JSON by default, or opt into TSV, XML, or image formats for networks.

Available tools

map_identifiers

Map protein identifiers to STRING IDs across species.

get_network_interactions

Retrieve protein-protein interaction networks for a set of proteins.

get_functional_enrichment

Perform functional enrichment analysis (GO, KEGG, etc.).

get_network_image

Generate network visualization images from interaction data.

get_version_info

Query the STRING database version information.

get_interaction_partners

Find all interaction partners for given proteins.

get_functional_annotation

Obtain detailed functional annotations for proteins.

get_protein_similarity

Calculate similarity scores between proteins.

get_ppi_enrichment

Test for protein-protein interaction enrichment.