Skip to main content
Glama

Uniprot

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Search

search
Read-onlyIdempotent

"Find protein [name]" / "look up [gene] in UniProt" / "BRCA1 / TP53 / insulin protein info" / "all proteins for [organism]" — UniProtKB search via Lucene-style queries (e.g. gene:BRCA1 AND organism_id:9606 for human BRCA1). UniProt is the authoritative protein-sequence-and-function database — use for protein characterization, function annotation, sequence retrieval, and cross-references to PDB/GO/PubMed.

Input Schema

NameRequiredDescriptionDefault
sizeNo1-500 (default 25)
queryYesLucene-style expression, passed bare — do NOT wrap the whole thing in quotes. Fielded terms combine with AND, e.g. gene:BRCA1 AND organism_id:9606. Quotes are only for a multi-word value, e.g. organism_name:"Homo sapiens". Plain-English questions match poorly because every token must appear; prefer keywords.
fieldsNoComma-sep returned fields (json/tsv only).
formatNojson (default) | tsv | fasta | xml

Output Schema

NameRequiredDescriptionDefault
facetsNoSearch facets for filtering
resultsNoArray of search result entries

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / query / description
      Added value: +"Lucene-style expression, passed bare — do NOT wrap the whole thing in quotes. Fielded terms combine with AND, e.g. gene:BRCA1 AND organism_id:9606. Quotes are only for a multi-word value, e.g. organism_name:\"Homo sapiens\". Plain-English questions match poorly because every token must appear; prefer keywords."
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds that UniProt is the authoritative database and gives query syntax hints. No contradictions.

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

Conciseness4/5

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

The description is dense and front-loaded with examples. It efficiently conveys purpose, usage, and caveats without excess. Could be slightly shorter but effective.

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?

Covers all essential aspects: purpose, query format, output formats, database authority, and use cases. Output schema exists so return values are not needed. No gaps.

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% with all parameters described. The description adds extra value by explaining query syntax, fielded terms, and quoting rules, which goes beyond the schema.

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 clearly states the tool searches UniProtKB for protein information, with specific examples like 'find protein BRCA1'. It differentiates from siblings by focusing on UniProtKB search, unlike other tools like 'search_within'.

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?

The description advises when to use the tool (protein characterization, sequence retrieval, etc.) and warns against plain-English queries. It doesn't explicitly contrast with sibling tools but provides clear context for appropriate use.

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

All Uniprot toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources