find_databases
Identify relevant biological databases by searching with keywords like gene, pathway, or disease. Returns 1-3 scoped candidates for efficient workflow.
Instructions
Database discovery — REQUIRED first step for any TogoMCP workflow.
Always call this BEFORE get_MIE_file() or run_sparql(). Pass any search
terms you have (gene, pathway, drug target, variant, organism, disease,
enzyme class, etc.) as keywords. Returns 1–3 candidate databases scoped
to your terms — much more efficient than browsing the full catalog.
Workflow:
find_databases(keywords=[...]) — identify 1–3 relevant databases.
get_MIE_file(database) — learn each candidate's schema and SPARQL idioms.
run_sparql() — query with the discovered structured properties.
Common keywords to try: "MANE" (Ensembl), "drug targets" (ChEMBL), "clinical variants" (ClinVar), "pathways" (Reactome), "variants" (gnomAD), "ortholog" (OMA), "expression" (Bgee).
If you have no search terms and want to browse the full catalog instead, see
list_databases() — that tool is supplementary, not a substitute for this one.
Returns:
JSON string: a bare array of dicts
{database, title, matched_keywords, categories, snippet} (or
description when verbose=True). Sorted by number of matched keywords
descending, then alphabetically by database name.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| match | No | 'any' returns DBs matching at least one keyword (OR); 'all' requires every keyword to match (AND). | any |
| verbose | No | If True, return the full description; if False (default), return a short snippet around the first match. | |
| category | No | Category filter (substring, case-insensitive). Call list_categories() to see the available set. | |
| keywords | No | Keyword or list of keywords (case-insensitive substring match against title, description, and the database's curated keywords field). |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |