STRING MCP Server

This is the official remote Model Context Protocol endpoint for the STRING protein-protein interaction database. It is intended for MCP-compatible AI agents and applications.

Remote MCP endpoint:

https://mcp.string-db.org/

Use this URL in an MCP client that supports remote servers over Streamable HTTP.

What is STRING MCP?

STRING MCP connects AI agents to STRING data through the Model Context Protocol (MCP).

The server is designed for agent use. Responses are structured for reliable model interpretation, with adaptive trimming that keeps the most relevant data for grounding and token efficiency. In addition, the server attaches response metadata hints to help models understand returned results and choose useful follow-up queries.

How to use the remote server

Open the settings or connector configuration in an MCP-compatible client and add a remote MCP server. The exact interface depends on the client. The fields are typically similar to: 

Name: STRING database
URL: https://mcp.string-db.org/

Some clients may call this a custom connector, remote MCP server, HTTP MCP server, or simply an MCP server.

After connecting, ask your AI assistant biological questions that require STRING data, for example: 

Find interaction partners of TP53 in human.
Run functional enrichment for these proteins: TP53, MDM2, CDKN1A, ATM.
Which human proteins are associated with neuronal migration?
Find homologs of human EGFR in mouse.

Documentation

STRING chat

STRING also provides a live chat interface where you can try the MCP server with STRING data directly. This is a convenient way to test the available tools before configuring your own agent.

Go to string-db.org/cgi/chat.

Run it locally

The hosted endpoint above is the usual way to use the STRING MCP server. The open source server code can also be run locally for development, extension, testing, or reproducible workflows.

Source code: github.com/meringlab/string-mcp 

git clone https://github.com/meringlab/string-mcp.git
cd string-mcp
pip install -r requirements.txt
python server.py

License / Citation

Data accessed through this remote endpoint is available under the CC BY 4.0 License. It is free to use without restrictions for commercial and non-commercial purposes.

Publications, workflows, and other outputs using STRING data or this remote endpoint must acknowledge STRING and cite the latest STRING manuscript.

API

For non-agentic programmatic access to STRING, use the regular STRING API instead.

Agent Skill

The repository includes an optional Agent Skill with instructions for STRING network and enrichment analysis workflows.

Available tools

Tool Description
string_resolve_proteins Resolve protein identifiers to STRING metadata.
string_interactions_query_set Retrieve interactions within a query protein set.
string_all_interaction_partners Find interaction partners for one or more proteins.
string_visual_network Generate a STRING network image URL.
string_network_clustering Cluster a STRING interaction network.
string_network_link Create an interactive STRING network link.
string_homology Find homologs in selected species or clades.
string_interaction_evidence Link to STRING evidence pages for protein pairs.
string_enrichment Run functional enrichment analysis.
string_functional_annotation Retrieve curated functional annotations.
string_enrichment_image_url Generate an enrichment figure image URL.
string_ppi_enrichment Test whether a protein set is enriched for interactions.
string_proteins_for_term Find proteins associated with a function, pathway, disease, tissue, or compartment.
string_sequence_search Search STRING proteins by amino acid sequence.
string_query_species Search species and clades available in STRING.
string_create_file Create a downloadable STRING result file.
string_help Return STRING-specific help topics and limitations.