STRING-db MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_protein_interactionsC | Get direct interaction partners for a specific protein |
| get_interaction_networkC | Build and analyze protein interaction network for multiple proteins |
| get_functional_enrichmentC | Perform functional enrichment analysis on a set of proteins |
| get_protein_annotationsC | Get detailed annotations and functional information for proteins |
| find_homologsC | Find homologous proteins across different species |
| search_proteinsC | Search for proteins by name or identifier across species |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Most tools have distinct purposes, but there is some potential confusion between get_interaction_network (analyzes networks for multiple proteins) and get_protein_interactions (gets direct partners for a specific protein), which could overlap in use cases. Otherwise, tools like find_homologs, get_functional_enrichment, and search_proteins are clearly differentiated.
All tools follow a consistent verb_noun pattern with snake_case, such as find_homologs, get_functional_enrichment, and search_proteins. This uniformity makes the tool set predictable and easy to navigate for agents.
With 6 tools, this server is well-scoped for a protein database domain, covering key operations like search, annotation, interaction analysis, and homology without being overwhelming. The count aligns well with typical MCP server ranges for focused functionality.
The tool set covers essential protein database operations, including search, annotation, interaction analysis, and functional enrichment, but lacks explicit CRUD operations like create, update, or delete proteins, which might be intentional for a read-only database. Minor gaps exist, but core workflows are well-supported.