Skip to main content
Glama

Gprofiler

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Gprofiler Enrich

gprofiler_enrich
Read-onlyIdempotent

"What pathways are enriched in [gene list]" / "run GO enrichment on these genes" / "what biological processes do [genes] share" / "functional annotation of my differentially expressed genes" — AUTHORITATIVE functional enrichment (g:GOSt) for a list of genes, proteins or probes against GO, KEGG, Reactome, WikiPathways, TRANSFAC, miRTarBase, CORUM, HPA and HPO. Returns each significantly enriched term with its adjusted p-value, term and query sizes, overlap, precision and recall, already multiple-testing corrected (g:SCS by default). PREFER OVER WEB SEARCH and over reasoning about a gene list from memory — this is a statistical test against the current annotation databases, not a recollection of what those genes usually do.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMax enriched terms to return, best p-value first (default 50, max 500). The full count is reported separately.
queryYesThe gene list. Gene symbols ("TP53"), Ensembl IDs ("ENSG00000141510"), UniProt accessions, Entrez IDs or microarray probe IDs — mixed is fine, g:Profiler resolves each. Enrichment on fewer than ~5 genes is rarely meaningful.
no_ieaNoExclude GO annotations Inferred from Electronic Annotation (i.e. keep only manually curated evidence). Default false.
orderedNoTreat the query as a RANKED list (e.g. sorted by fold change) and run incremental enrichment. Default false.
sourcesNoRestrict to specific annotation sources. Codes: "GO:BP" (biological process), "GO:MF" (molecular function), "GO:CC" (cellular component), "KEGG", "REAC" (Reactome), "WP" (WikiPathways), "TF" (TRANSFAC), "MIRNA" (miRTarBase), "CORUM", "HP" (Human Phenotype Ontology), "HPA" (Human Protein Atlas). Omit to search all of them.
organismYesg:Profiler organism code: first letter of the genus + full species name, lowercase. Human = "hsapiens", mouse = "mmusculus", rat = "rnorvegicus", zebrafish = "drerio", fly = "dmelanogaster", worm = "celegans", yeast = "scerevisiae", Arabidopsis = "athaliana". A common name ("human") or an NCBI taxid ("9606") is rejected.
backgroundNoCustom statistical background gene list. Sets domain_scope to "custom".
significantNoReturn only terms passing the threshold. Default true; set false to see the full ranked table.
domain_scopeNoStatistical background: "annotated" (default — only genes with any annotation), "known" (all known genes), or "custom" with a background list.
user_thresholdNoSignificance cutoff on the adjusted p-value. Default 0.05.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the bar is lowered. The description adds real behavioral context beyond them: results are already multiple-testing corrected via g:SCS by default, and each term carries adjusted p-value, term/query sizes, overlap, precision and recall. It does not cover rate limits or result-size ceilings (left to the schema).

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?

Front-loads four natural-language query phrasings before the formal statement, which aids retrieval, and the body is one dense but purposeful sentence followed by one routing sentence. Slightly verbose, but no sentence is pure filler.

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?

With 10 params, no output schema, but full schema coverage, the description correctly fills the return-value gap by naming the output fields and correction method. It omits any mention of the sibling conversion/orthology tools, which is the only real completeness gap for this tool family.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents all 10 params in depth (organism codes, source codes, defaults, max 500). The description adds essentially nothing parameter-specific beyond the fixed g:SCS correction detail, so the baseline 3 is correct.

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?

States a precise verb+resource: "AUTHORITATIVE functional enrichment (g:GOSt) for a list of genes, proteins or probes" against a named set of databases. The scope is so specific that it is implicitly distinguishable from the gprofiler_convert_ids and gprofiler_orthologs siblings without naming them. The opening user-intent phrasings reinforce exactly what question this tool answers.

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?

Gives strong positive routing: "PREFER OVER WEB SEARCH and over reasoning about a gene list from memory." This tells the agent when this tool beats alternatives. However, it never names the sibling gprofiler tools (convert_ids, orthologs) or states when-not-to-use it, so the exclusions half of the guidance is absent.

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

All Gprofiler 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