Connects Claude to STRING, the protein interaction database covering roughly 12,000 organisms. You get five tools: resolve for mapping gene names or accessions to STRING IDs, interactions for pulling partner proteins, network for generating visual graphs with tabular data, enrichment for functional annotation against GO/KEGG/Reactome/Pfam, and homology for cross-species mappings. Runs through Pipeworx's gateway as a streamable HTTP service, so no local setup. Useful when you're doing comparative proteomics, pathway analysis, or need to quickly validate whether a set of proteins actually interact based on experimental and predicted data.
STRING-DB MCP — protein-protein interaction networks.
Part of Pipeworx — an MCP gateway connecting AI agents to 673+ live data sources.
| Tool | Description |
|---|---|
resolve | Map free-text identifiers (gene symbols, accessions) → STRING identifiers. |
interactions | Interaction partners for a set of proteins. |
network | Network image url + tabular interaction data. |
enrichment | Functional enrichment (GO, KEGG, Pfam, Reactome, …) for a gene set. |
homology | Homology mappings. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"string-db": {
"url": "https://gateway.pipeworx.io/string-db/mcp"
}
}
}
Or connect to the full Pipeworx gateway for access to all 673+ data sources:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Instead of calling tools directly, you can ask questions in plain English:
ask_pipeworx({ question: "your question about String Db data" })
The gateway picks the right tool and fills the arguments automatically.
MIT