STRING Database MCP Server

STRING: Perform network clustering

string_network_clustering

Performs network clustering on a STRING interaction network and returns both a network image URL and details about each detected cluster.

Use the same parameters as in the network creation step to ensure consistency. If the network already contains disconnected subgraphs, the resulting number of clusters may differ from the requested value.

Dashed lines represent connections between clusters, while solid lines indicate interactions within clusters.

Notes:

For small queries (≤5 proteins), the required_score parameter is automatically lowered to 0.
If only a single cluster is produced, try increasing required_score, adjusting the inflation parameter, or switching to kmeans for small, highly interconnected networks.

Input Schema

TableJSON Schema

Name	Required	Description
`species`	No
`proteins`	Yes	Required. One or more protein identifiers (optionally with values). Example: PTEN 0.234 SMO -3.445 Separate entries with newline (%0d). Numeric values (e.g. expression data) can be provided after identifiers.
`network_type`	No
`extend_network`	No
`network_flavor`	No
`required_score`	No
`center_node_labels`	No
`clustering_algorithm`	No
`clustering_parameter`	No
`hide_disconnected_nodes`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

TDQS

A4.7/5.0

Behavior5/5

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

With no annotations given, the description fully carries the burden of behavioral disclosure. It reveals important non-obvious behaviors: automatic lowering of required_score for ≤5 proteins, possible mismatch in cluster count for disconnected subgraphs, the meaning of dashed vs solid lines, and adjustment tips for single-cluster results. This exceeds typical descriptions.

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

Conciseness5/5

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

The description is well-structured: a concise opening sentence, a usage note, a visual-guide sentence, and a bulleted list of caveats. Every sentence contributes new information without verbosity, and the most important purpose is front-loaded.

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

Completeness5/5

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

Given the tool's complexity (10 parameters, 1 required), the description provides sufficient context for correct invocation. It covers the tool's core function, consistency with network creation, edge-case behavior, and troubleshooting adjustments. The presence of an output schema mitigates the need to describe return values in the text.

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?

The input schema already provides thorough descriptions for all 10 parameters, including defaults and examples. The description adds contextual meaning beyond the schema by explaining the relationship between required_score and small queries, and by elaborating on clustering_parameter behavior (inflation vs number of clusters) in the troubleshooting note.

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

Purpose5/5

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

The description opens with 'Performs network clustering on a STRING interaction network' and specifies the two outputs: a network image URL and details about each detected cluster. This clearly identifies the tool's purpose and differentiates it from siblings like string_visual_network by focusing on clustering results.

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 advises 'Use the same parameters as in the network creation step to ensure consistency,' which implies a workflow context. It also provides concrete troubleshooting guidance (adjusting required_score, inflation parameter, or switching to kmeans) but does not explicitly name alternative tools or state when not to use this tool.

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

All STRING Database MCP Server tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0

Disambiguation2/5

Several tool pairs have overlapping purposes: string_network_link and string_visual_network both return network URLs with nearly identical behavior, and string_all_interaction_partners vs string_interactions_query_set both query interactions, differing subtly in scope. The enrichment/annotation tools also share boundaries, making it difficult for agents to disambiguate without reading detailed descriptions.

Naming Consistency3/5

All tools share the 'string_' prefix, but the pattern is inconsistent: some are verb-first (create_file, resolve_proteins), some are noun-first (interactions_query_set, network_link), and some are bare nouns (enrichment, homology). This mixed convention reduces predictability.

Tool Count4/5

At 17 tools, the server is slightly above the ideal range, but it covers a broad domain: interactions, networks, enrichment, annotation, homology, species resolution, and sequence search. The count is justified by the complexity of the STRING database.

Completeness4/5

The tool set covers core STRING workflows: querying interactions, constructing networks, computing enrichment, retrieving annotations, identifying homologs, mapping IDs, and exporting data. Minor gaps exist (e.g., direct edge-list tables and intricate interaction score details), but the overall surface is robust.

STRING: Perform network clustering

Input Schema

Output Schema

TDQS

Glama MCP Gateway

TDQS

Resources