search_go_termsLABSCO SUMMARY
GO terms answered from the ontology, not from memory.
A GO id looks plausible whether or not it exists. This resolves them against QuickGO, so the identifier that goes into a pipeline is one that was checked rather than one that looked right.
What it is
A read layer over the Gene Ontology, served from EBI's QuickGO API. Terms can be searched by keyword or fetched by identifier, and the ontology's own statistics sit alongside them.
What you get
- GO terms searched by keyword, name or definition, scoped to one branch such as biological_process
- The full record for a term you name by its GO id
- An identifier checked for both format and existence before you build on it
- Ontology statistics: term counts and how recently each branch was updated
- Resource paths for a term, its hierarchy, a gene's annotations and a search, addressable directly
Requirements
Node with npm install and npm run build, then one stdio entry in your client config. No account and no key — everything comes from public Gene Ontology data via QuickGO.
Setup effort
Build from source
USE CASES
01
Finding the right term for a process
Search by keyword inside one branch of the ontology and pick from real terms instead of guessing at an id.
02
Reading what a GO id actually means
Fetch the full record for an identifier you found in a paper or a results table.
03
Catching a bad identifier before the analysis runs
Format and existence checked in one call, which is cheaper than debugging an empty enrichment result.
04
Knowing how current the ontology is
Term counts and update dates per branch, for the work where the vintage of the ontology changes the result.
4 tools
Listed in project docs. Your client may show a different list.
get_go_termvalidate_go_idget_ontology_statsBEFORE YOU INSTALL
What to know first
Tools you get
4 tools named in the project's documentation.
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone and build this one yourself.
Server setup
TERMINAL
git clone https://github.com/Augmented-Nature/GeneOntology-MCP-Server
cd GeneOntology-MCP-Server
npm install
npm run buildAdd the mcpServers block below to your MCP client configuration
MCP Clients
Any MCP client
ANY MCP CLIENT · JSON
{
"mcpServers": {
"go-server": {
"command": "node",
"args": [
"<YOUR_PATH_TO_GO_SERVER>/build/index.js"
]
}
}
}
