Skip to main content
Glama

Jean by Melad Labs

by app.vercel.jeanslabs
OverviewDiscussionsAdmin

query_database

Read-only

Ask one of the ~60 authoritative databases a question and hand its rows downstream — Ensembl, UniProt, ClinVar, gnomAD, ChEMBL, PubChem, InterPro, STRING, PDB, AlphaFold, the GWAS Catalog, PubMed and the rest. Nothing here computes science: a connector returns what the authority already published, which is the rule that an authoritative registry outranks anything kept locally.

Input Schema

NameRequiredDescriptionDefault
limitNocap on rows returned, where the authority honours one.
queryYeswhat to ask, in the authority's own terms — an identifier, a gene symbol, or one of its command forms such as `ensembl_lookup:BRCA2`.
_filesNoThe project: record references shaped like _subject. Their records become library documents a tool names in sequences/parts/document; a trace or alignment is found by file name.
_subjectNoThe record to act on: exactly one of sequence, accession (+source), sample (an id from list_samples) or file ({name, text} or {name, base64}); record_index picks one record of several.
authorityYeswhich database to ask. Values: pubmed (NCBI PubMed (E-utilities) — literature), pmc-idconv (NCBI PMC ID Converter — literature), europepmc (Europe PMC — literature), openalex (OpenAlex — literature), crossref (Crossref — literature), arxiv (arXiv — literature), biorxiv (bioRxiv — literature), medrxiv (medRxiv — literature), datacite (DataCite — literature), ensembl (Ensembl REST — genomics), ucsc (UCSC Genome Browser API — genomics), biomart (Ensembl BioMart — genomics), mygene (MyGene.info — genomics), ncbi-gene (NCBI Gene (E-utilities) — genomics), hgnc (HGNC (genenames.org) — genomics), gnomad (gnomAD (Broad) — genomics), clinvar (NCBI ClinVar — genomics), dbsnp (NCBI dbSNP — genomics), variation (NCBI Variation Services — genomics), cadd (CADD (Kircher lab) — genomics), gtex (GTEx Portal — genomics), eqtlcatalogue (eQTL Catalogue (EBI) — genomics), gwascatalog (GWAS Catalog (EBI/NHGRI) — genomics), pheweb (PheWeb / FinnGen — genomics), uniprot (UniProt — proteins), interpro (InterPro / Pfam (EBI) — proteins), string (STRING — proteins), proteinatlas (Human Protein Atlas — proteins), alphafold (AlphaFold DB (EBI) — proteins), pdb (RCSB PDB — proteins), emdb (EMDB (EBI) — proteins), complexportal (Complex Portal (EBI) — proteins), intact (IntAct (EBI) — proteins), chembl (ChEMBL (EBI) — chemistry), pubchem (PubChem (NCBI) — chemistry), chebi (ChEBI (EBI) — chemistry), bindingdb (BindingDB — chemistry), zinc (ZINC (CartBlanche, UCSF) — chemistry), rhea (Rhea (EBI) — chemistry), clinicaltrials (ClinicalTrials.gov — clinical), openfda (openFDA — clinical), opentargets (Open Targets Platform — clinical), civic (CIViC — clinical), clingen (ClinGen (erepo.genome.network) — clinical), cosmic (COSMIC via NLM Clinical Tables — clinical), depmap (Cell Model Passports (Sanger) — clinical), cbioportal (cBioPortal — clinical), geo (NCBI GEO — omics), arrayexpress (ArrayExpress / BioStudies (EBI) — omics), pride (PRIDE (EBI) — omics), metabolights (MetaboLights (EBI) — omics), mgnify (MGnify (EBI) — omics), encode (ENCODE Project — omics), jaspar (JASPAR (Elixir) — omics), unibind (UniBind (Univ. of Oslo) — omics), cellguide (CellGuide (CZI CELLxGENE) — cells), panglaodb (PanglaoDB — cells), antibodyregistry (Antibody Registry (RRID) — cells), ols (OLS4 (EBI) — ontology), quickgo (QuickGO (EBI) — ontology), identifiers-org (identifiers.org registry — ontology), ncbi-taxonomy (NCBI Taxonomy (E-utilities) — ontology), reactome (Reactome — ontology), kegg (KEGG — ontology), rfam (Rfam (EBI) — ontology), grantsgov (Grants.gov — funding).

Output Schema

NameRequiredDescriptionDefault
countYeshow many rows came back
resultsYesthe rows the authority returned — wire into filter_items, check_rows or summarize_rows
envelopeYesthe whole response, for a row shape this node's `results` does not name
authorityYeswhich authority answered, stated rather than implied
endpointsYesthe URLs actually called — the provenance a methods section needs
retrievedAtYeswhen it was fetched, because a live lookup is a fact about a moment

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / authority / description
      Previous value: -"which database to ask. Values: pubmed (NCBI PubMed (E-utilities) — literature), pmc-idconv (NCBI PMC ID Converter — literature), europepmc (Europe PMC — literature), openalex (OpenAlex — literature), crossref (Crossref — literature), arxiv (arXiv — literature), biorxiv (bioRxiv — literature), medrxiv (medRxiv — literature), datacite (DataCite — literature), ensembl (Ensembl REST — genomics), ucsc (UCSC Genome Browser API — genomics), biomart (Ensembl BioMart — genomics), mygene (MyGene.info — genomics), gnomad (gnomAD (Broad) — genomics), clinvar (NCBI ClinVar — genomics), dbsnp (NCBI dbSNP — genomics), variation (NCBI Variation Services — genomics), cadd (CADD (Kircher lab) — genomics), gtex (GTEx Portal — genomics), eqtlcatalogue (eQTL Catalogue (EBI) — genomics), gwascatalog (GWAS Catalog (EBI/NHGRI) — genomics), pheweb (PheWeb / FinnGen — genomics), uniprot (UniProt — proteins), interpro (InterPro / Pfam (EBI) — proteins), string (STRING — proteins), proteinatlas (Human Protein Atlas — proteins), alphafold (AlphaFold DB (EBI) — proteins), pdb (RCSB PDB — proteins), emdb (EMDB (EBI) — proteins), complexportal (Complex Portal (EBI) — proteins), intact (IntAct (EBI) — proteins), chembl (ChEMBL (EBI) — chemistry), pubchem (PubChem (NCBI) — chemistry), chebi (ChEBI (EBI) — chemistry), bindingdb (BindingDB — chemistry), zinc (ZINC (CartBlanche, UCSF) — chemistry), rhea (Rhea (EBI) — chemistry), clinicaltrials (ClinicalTrials.gov — clinical), openfda (openFDA — clinical), opentargets (Open Targets Platform — clinical), civic (CIViC — clinical), clingen (ClinGen (erepo.genome.network) — clinical), cosmic (COSMIC via NLM Clinical Tables — clinical), depmap (Cell Model Passports (Sanger) — clinical), cbioportal (cBioPortal — clinical), geo (NCBI GEO — omics), arrayexpress (ArrayExpress / BioStudies (EBI) — omics), pride (PRIDE (EBI) — omics), metabolights (MetaboLights (EBI) — omics), mgnify (MGnify (EBI) — omics), encode (ENCODE Project — omics), jaspar (JASPAR (Elixir) — omics), unibind (UniBind (Univ. of Oslo) — omics), cellguide (CellGuide (CZI CELLxGENE) — cells), panglaodb (PanglaoDB — cells), antibodyregistry (Antibody Registry (RRID) — cells), ols (OLS4 (EBI) — ontology), quickgo (QuickGO (EBI) — ontology), reactome (Reactome — ontology), kegg (KEGG — ontology), rfam (Rfam (EBI) — ontology), grantsgov (Grants.gov — funding)."New value: +"which database to ask. Values: pubmed (NCBI PubMed (E-utilities) — literature), pmc-idconv (NCBI PMC ID Converter — literature), europepmc (Europe PMC — literature), openalex (OpenAlex — literature), crossref (Crossref — literature), arxiv (arXiv — literature), biorxiv (bioRxiv — literature), medrxiv (medRxiv — literature), datacite (DataCite — literature), ensembl (Ensembl REST — genomics), ucsc (UCSC Genome Browser API — genomics), biomart (Ensembl BioMart — genomics), mygene (MyGene.info — genomics), ncbi-gene (NCBI Gene (E-utilities) — genomics), hgnc (HGNC (genenames.org) — genomics), gnomad (gnomAD (Broad) — genomics), clinvar (NCBI ClinVar — genomics), dbsnp (NCBI dbSNP — genomics), variation (NCBI Variation Services — genomics), cadd (CADD (Kircher lab) — genomics), gtex (GTEx Portal — genomics), eqtlcatalogue (eQTL Catalogue (EBI) — genomics), gwascatalog (GWAS Catalog (EBI/NHGRI) — genomics), pheweb (PheWeb / FinnGen — genomics), uniprot (UniProt — proteins), interpro (InterPro / Pfam (EBI) — proteins), string (STRING — proteins), proteinatlas (Human Protein Atlas — proteins), alphafold (AlphaFold DB (EBI) — proteins), pdb (RCSB PDB — proteins), emdb (EMDB (EBI) — proteins), complexportal (Complex Portal (EBI) — proteins), intact (IntAct (EBI) — proteins), chembl (ChEMBL (EBI) — chemistry), pubchem (PubChem (NCBI) — chemistry), chebi (ChEBI (EBI) — chemistry), bindingdb (BindingDB — chemistry), zinc (ZINC (CartBlanche, UCSF) — chemistry), rhea (Rhea (EBI) — chemistry), clinicaltrials (ClinicalTrials.gov — clinical), openfda (openFDA — clinical), opentargets (Open Targets Platform — clinical), civic (CIViC — clinical), clingen (ClinGen (erepo.genome.network) — clinical), cosmic (COSMIC via NLM Clinical Tables — clinical), depmap (Cell Model Passports (Sanger) — clinical), cbioportal (cBioPortal — clinical), geo (NCBI GEO — omics), arrayexpress (ArrayExpress / BioStudies (EBI) — omics), pride (PRIDE (EBI) — omics), metabolights (MetaboLights (EBI) — omics), mgnify (MGnify (EBI) — omics), encode (ENCODE Project — omics), jaspar (JASPAR (Elixir) — omics), unibind (UniBind (Univ. of Oslo) — omics), cellguide (CellGuide (CZI CELLxGENE) — cells), panglaodb (PanglaoDB — cells), antibodyregistry (Antibody Registry (RRID) — cells), ols (OLS4 (EBI) — ontology), quickgo (QuickGO (EBI) — ontology), identifiers-org (identifiers.org registry — ontology), ncbi-taxonomy (NCBI Taxonomy (E-utilities) — ontology), reactome (Reactome — ontology), kegg (KEGG — ontology), rfam (Rfam (EBI) — ontology), grantsgov (Grants.gov — funding)."
    • changedInput schema / properties / authority / enum
      Previous value: -[
-  "pubmed",
-  "pmc-idconv",
-  "europepmc",
-  "openalex",
-  "crossref",
-  "arxiv",
-  "biorxiv",
-  "medrxiv",
-  "datacite",
-  "ensembl",
-  "ucsc",
-  "biomart",
-  "mygene",
-  "gnomad",
-  "clinvar",
-  "dbsnp",
-  "variation",
-  "cadd",
-  "gtex",
-  "eqtlcatalogue",
-  "gwascatalog",
-  "pheweb",
-  "uniprot",
-  "interpro",
-  "string",
-  "proteinatlas",
-  "alphafold",
-  "pdb",
-  "emdb",
-  "complexportal",
-  "intact",
-  "chembl",
-  "pubchem",
-  "chebi",
-  "bindingdb",
-  "zinc",
-  "rhea",
-  "clinicaltrials",
-  "openfda",
-  "opentargets",
-  "civic",
-  "clingen",
-  "cosmic",
-  "depmap",
-  "cbioportal",
-  "geo",
-  "arrayexpress",
-  "pride",
-  "metabolights",
-  "mgnify",
-  "encode",
-  "jaspar",
-  "unibind",
-  "cellguide",
-  "panglaodb",
-  "antibodyregistry",
-  "ols",
-  "quickgo",
-  "reactome",
-  "kegg",
-  "rfam",
-  "grantsgov"
-]New value: +[
+  "pubmed",
+  "pmc-idconv",
+  "europepmc",
+  "openalex",
+  "crossref",
+  "arxiv",
+  "biorxiv",
+  "medrxiv",
+  "datacite",
+  "ensembl",
+  "ucsc",
+  "biomart",
+  "mygene",
+  "ncbi-gene",
+  "hgnc",
+  "gnomad",
+  "clinvar",
+  "dbsnp",
+  "variation",
+  "cadd",
+  "gtex",
+  "eqtlcatalogue",
+  "gwascatalog",
+  "pheweb",
+  "uniprot",
+  "interpro",
+  "string",
+  "proteinatlas",
+  "alphafold",
+  "pdb",
+  "emdb",
+  "complexportal",
+  "intact",
+  "chembl",
+  "pubchem",
+  "chebi",
+  "bindingdb",
+  "zinc",
+  "rhea",
+  "clinicaltrials",
+  "openfda",
+  "opentargets",
+  "civic",
+  "clingen",
+  "cosmic",
+  "depmap",
+  "cbioportal",
+  "geo",
+  "arrayexpress",
+  "pride",
+  "metabolights",
+  "mgnify",
+  "encode",
+  "jaspar",
+  "unibind",
+  "cellguide",
+  "panglaodb",
+  "antibodyregistry",
+  "ols",
+  "quickgo",
+  "identifiers-org",
+  "ncbi-taxonomy",
+  "reactome",
+  "kegg",
+  "rfam",
+  "grantsgov"
+]
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds meaningful non-obvious behavior: it is a pass-through connector to external registries, results are what the authority published, and authoritative registries outrank local data. It omits per-authority auth requirements, rate limits, and failure behavior for unavailable connectors.

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?

Two sentences, front-loaded with the action and scope, then a short rationale for why connectors behave the way they do. The second sentence is longer than strictly necessary but it earns its place by establishing the authority-over-local-data rule. Minor verbosity in the database enumeration, which the enum already lists.

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 shapes need not be explained, and all five parameters are documented in the schema with 100% coverage including the nested _subject object. The description covers purpose and the pass-through behavioral model; the only real gap is sibling differentiation from the dedicated lookup_* tools, which matters given how many lookups populate the sibling list.

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% and the authority enum already documents all 60+ databases, so the schema does the heavy lifting. The description adds only the notion that the query is expressed 'in the authority's own terms', which the schema's query description already conveys via the ensembl_lookup:BRCA2 example. Baseline 3 applies.

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 states a specific verb and resource ('ask one of the ~60 authoritative databases a question and hand its rows downstream') and names concrete authorities, so the agent knows exactly what class of operation this is. It does not, however, distinguish itself from dedicated siblings like lookup_gene, lookup_variant or search_literature, leaving ambiguity about when a federated query beats a purpose-built lookup.

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

Usage Guidelines3/5

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

The line 'Nothing here computes science: a connector returns what the authority already published' implies the tool is for retrieving published records rather than computing derived results, which is useful framing. But no explicit when-to-use/when-not or named alternative is given, so the agent must infer that query_database replaces (or complements) lookup_gene, search_literature, fetch_record, etc.

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

All Jean by Melad Labs 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