GTDB-MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GTDB_DATA_DIR | No | Path to external GTDB data directory. If not set, the server uses the built-in curated reference dataset. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| searchA | Search for taxa or genomes in the GTDB database by name. Returns matching organisms, taxonomic groups, and genome assemblies. Supports partial matching (e.g., 'Bacillus' will match 'Bacillus subtilis', 'Bacillus cereus', etc.). |
| get_taxonomyB | Get the complete taxonomic lineage of an organism or taxon from GTDB. Returns the full classification from domain down to species level (d__Domain; p__Phylum; c__Class; o__Order; f__Family; g__Genus; s__Species). |
| get_taxon_summaryA | Get a comprehensive summary of a taxonomic group, including genome counts, species counts, child taxa, and description. Useful for understanding the diversity and composition of any taxonomic level. |
| get_childrenA | Get the direct child taxa of a given taxon in the GTDB taxonomy. For example, children of 'Bacillales' include 'Bacillaceae', 'Staphylococcaceae', etc. |
| list_phylaA | List all bacterial or archaeal phyla in GTDB. This is the starting point for exploring the taxonomy tree from the top level. |
| list_taxa_by_rankB | List all taxa at a specific taxonomic rank, optionally filtered by domain. Useful for browsing the taxonomy at any level. |
| get_genomeA | Get detailed information about a specific genome by its GTDB genome ID (e.g., GCF_000005845.2). Returns taxonomy, genome size, GC content, quality metrics, and type strain status. |
| get_genomes_for_speciesA | Get all genome assemblies classified under a given species in GTDB. Useful for finding reference genomes and type strains. |
| get_genomes_for_taxonB | Get all genome assemblies classified under a given taxonomic group. For example, get all genomes in the family Enterobacteriaceae or phylum Bacillota. |
| compare_genomesA | Compare two genomes taxonomically. Returns the shared lineage, lowest common ancestor (LCA), differing ranks, and genome metric differences (size, GC content). |
| get_tree_pathA | Get the phylogenetic tree path between two taxa. Shows the route through the taxonomy tree from one taxon to another via their lowest common ancestor (LCA). |
| get_database_statsA | Get statistics about the GTDB database, including version, release date, total genome counts, and taxonomic diversity metrics for both bacteria and archaea. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 12 tools
Most tools have clearly distinct purposes, but a few overlap: list_phyla is a special case of list_taxa_by_rank, get_children is subsumed by get_taxon_summary, and get_genomes_for_species is a convenience wrapper around get_genomes_for_taxon. Descriptions help clarify intended use, so misselection is unlikely but not impossible.
All tools use snake_case with a predictable verb_noun or verb_object pattern (get_taxonomy, list_phyla, compare_genomes, get_database_stats). The lone exception is 'search', which lacks an explicit noun, but this is a minor deviation from an otherwise consistent convention.
12 tools is well-scoped for a taxonomic and genomic reference database; each tool covers a distinct exploration or retrieval operation without excessive fragmentation. No tool feels redundant enough to remove, and the set is not bloated.
The surface covers search, taxonomy traversal, genome retrieval, comparison, and database statistics, which is comprehensive for a read-only reference database. Minor gaps such as batch operations or sequence retrieval are outside the apparent scope and do not create dead ends.