Official STRING Database MCP Server

Overview Schema Source Related Servers Discussions Admin

STRING: Get interactions within query set

string_interactions_query_set

Retrieves interaction networks among a set of query proteins from STRING, including direct interactions for multiple proteins or a single protein's top partners.

Instructions

Retrieves the interactions between the query proteins. Use this method only when you specifically need to list the interactions between all proteins in your query set.

For a single protein, the network includes that protein and its top 10 most likely interaction partners, plus all interactions among those partners.
For multiple proteins, the network includes all direct interactions between them.
STRING does not store or report information about self-interactions/homomers; if asked, explain the limitation.

If few or no interactions are returned, consider reducing the required_score.

For large query sets (>50 proteins), consider increasing the required_score (e.g. ≥700) to focus on high-confidence interactions and avoid overly dense networks.

Expand the names of score sources:
nscore (neighborhood), fscore (fusion), pscore (phylogenetic profile),
ascore (coexpression), escore (experimental), dscore (database), tscore (text-mining)

Input Schema

TableJSON Schema

Name	Required	Description
`species`	No	NCBI taxonomy ID (e.g. 9606 for human) or STRING genome ID (e.g. STRG0AXXXXX for uploaded genomes).
`proteins`	Yes	One or more protein identifiers, separated by carriage return (%0d).
`network_type`	No	Omit for the default functional network. Its typed view can include physical and directed regulatory attributes when STRING returns them; inspect `physical` and `regulatory.directions` before claiming those edge types. Set physical for binding, complex, or co-complex questions. Set regulatory for directed regulatory relationships between proteins.
`extend_network`	No	Number of additional proteins to add to the network based on their connectivity. Default is 10 for a single protein query and 0 for multiple proteins. Set only if the user asks to add, extend, include a neighborhood, or show connecting proteins.
`network_flavor`	No	Defaults are typed for functional networks, evidence for physical networks, and confidence for regulatory networks. Typed returns functional pairs with any physical and directed regulatory attributes that STRING reports; it does not make every pair physical or regulatory. Typed is available only for functional networks. Set evidence or confidence only when the user requests that edge display style.
`required_score`	No	Minimum confidence score for an interaction. Omit unless a confidence threshold is requested or a broader/narrower threshold is needed.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.13.0Sep 30, 2026

TDQS

A3.9/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and does substantial work: it explains how the returned network is constructed for single vs. multiple proteins, and discloses the important limitation that STRING does not store/report self-interactions or homomers. It does not mention permissions, rate limits, or response shape, but output schema exists to cover returns.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core purpose and usage constraints are front-loaded, but the trailing bullet expanding 'score sources' (nscore, fscore, etc.) has no clear connection to this tool's parameters and reads like leftover content from a sibling evidence tool, adding noise that an agent must triage.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be described, and the description covers the remaining essentials: network construction semantics, a domain limitation, and threshold-tuning heuristics. It is largely complete for an agent to call the tool correctly, with the only gap being the ambiguous score-source glossary.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds value beyond the schema by explaining required_score behaviour (lower it for sparse results, raise to ≥700 for dense >50-protein sets) and by clarifying network composition tied to the proteins parameter. The score-source glossary at the end, however, references names that are not parameters of this tool, which weakens the parameter guidance.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb+resource ('Retrieves the interactions between the query proteins') and immediately scopes it with 'Use this method only when you specifically need to list the interactions between all proteins in your query set.' That scoping implicitly distinguishes it from string_all_interaction_partners (single-protein partner lookup), though it never names the sibling explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear when-to-use framing ('only when you specifically need...') and offers actionable tuning guidance: reduce required_score when few/no interactions return, raise it (≥700) for large query sets (>50 proteins). It stops short of explicitly naming alternative tools to use instead for other scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server