get_protein_interactionsLABSCO SUMMARY
The STRING workflow — search, expand, enrich — without leaving the analysis you are writing.
Search resolves a name you can say out loud into identifiers STRING accepts, the network call expands a gene list into its interactions, and enrichment turns that set into GO and KEGG terms. That is the loop, and it happens where the write-up is happening.
What it is
An unofficial server over the STRING protein interaction database: interaction partners, multi-protein networks, functional enrichment, annotations and cross-species homologs.
What you get
- Direct interaction partners for a protein, with confidence scores and evidence types
- An interaction network built and analysed across several proteins at once
- Functional enrichment over a protein set using GO terms, KEGG pathways and other annotations
- Detailed annotations and functional information for a protein
- Homologous proteins found across species for comparative work
- Proteins searched by name or identifier across multiple species
- The same data reachable as resources, addressed by protein or taxon ID
Requirements
Node, with the project built locally before first use. Augmented-Nature wrote it against STRING's public API, so it needs network access.
Setup effort
Build from source
USE CASES
01
Working out what a protein you just read about interacts with
Find the identifier by name, then pull its partners with confidence scores and evidence types.
02
Making sense of a gene list from an experiment
Build the interaction network across the whole set, then run functional enrichment on it.
03
Checking whether a finding carries across species
Find the homologs in mouse or rat and compare the interaction picture.
04
Filling in the background on a protein for a write-up
Read the annotations and functional information rather than paraphrasing another paper.
6 tools
Listed in project docs. Your client may show a different list.
get_interaction_networkget_functional_enrichmentget_protein_annotationsfind_homologssearch_proteinsBEFORE YOU INSTALL
What to know first
Tools you get
6 tools named in the project's documentation.
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone and build this one yourself.
Server setup
TERMINAL
git clone https://github.com/Augmented-Nature/STRING-db-MCP-Server
cd STRING-db-MCP-Server
npm install
npm run buildMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"string-server": {
"command": "node",
"args": [
"<YOUR_PATH_TO_STRING_SERVER>/build/index.js"
]
}
}
}
