Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PYTHONPATHNoPath to the src directory, needed only when running from a source install without adding the package to PATH (e.g. "/path/to/eggNOG-MCP/src").

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

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}

Tools

Functions exposed to the LLM to take actions

NameDescription
get_proteinB

Look up detailed information for a protein in the eggNOG database.

Retrieves protein family membership, predicted functions (KEGG KO terms and GO terms with confidence scores), and the list of orthologous groups (OGs) associated with the protein.

Parameters

protein_id : str The eggNOG protein identifier in the format taxid.seqid. Examples: - 9606.ENSP00000269305 (human P53 / TP53) - 9606.ENSP00000330696 (human P2RX7) - 460265.Mnod_3996 (nitrogen fixation protein)

Returns

str JSON string with protein family, function predictions, and OG list.

get_orthologous_groupA

Look up information for an orthologous group (OG) in eggNOG.

Retrieves the evolutionary origin, protein count, species count, functional annotation (KEGG KO and GO slim terms), and the list of all OGs in the same protein family.

Parameters

og_id : str The orthologous group identifier in the format family@taxid|level. Examples: - P53@33154|A-1 (P53 family, Opisthokonta level) - P53@7742|IM-18 (P53 family, Gnathostomata level)

Returns

str JSON string with OG details including evolutionary origin, counts, and functional annotation.

get_og_contentA

Retrieve the list of proteins within an orthologous group.

Returns the species and their protein members for the specified OG. The result is capped at max_species to avoid excessively large responses.

Parameters

og_id : str The orthologous group identifier in family@taxid|level format. Example: P53@33154|A-1 max_species : int, optional Maximum number of species to include (default 50).

Returns

str JSON string with species list, protein counts, and protein IDs.

get_orthologsB

Retrieve pairwise orthologs for a protein.

Returns the orthologous proteins grouped by species for the given eggNOG protein ID.

Parameters

protein_id : str The eggNOG protein identifier in taxid.seqid format. Example: 9606.ENSP00000269305 max_species : int, optional Maximum number of species to include (default 50).

Returns

str JSON string with orthologs grouped by species.

search_eggnogA

Search the eggNOG database for proteins or protein families.

Performs a text search across the eggNOG database. The query must be at least 3 characters long. The query can be a protein name (e.g. P53), a UniProt ID (e.g. P04637), or a protein family name.

Parameters

query : str Search query string (minimum 3 characters). Examples: - P53 - P04637 - TP53 - P2RX7

Returns

str JSON string with a list of search results (type, ID, label, URL).

annotate_proteinA

Annotate a protein with functional information from eggNOG.

Returns a structured functional annotation for the given protein, including KEGG KO terms, GO slim terms, protein family, Pfam domains, and orthologous groups. This is a higher-level convenience wrapper around get_protein that emphasises the annotation results.

Parameters

protein_id : str The eggNOG protein identifier in the format taxid.seqid. Examples: - 9606.ENSP00000269305 (human P53) - 4932.YJR154W (yeast)

Returns

str JSON string with KEGG KO terms, GO terms, and cross-references.

get_protein_familyB

Retrieve protein family (cluster) content from eggNOG.

Returns the list of species and proteins grouped under the given protein family name (also called a cluster).

Parameters

family_name : str The protein family / cluster name. Examples: P53, P53_tetramer, P53_TAD max_species : int, optional Maximum number of species to include (default 50).

Returns

str JSON string with species list, protein counts, and protein IDs.

get_database_statsA

Retrieve summary statistics of the eggNOG 7 database.

Returns the number of annotated species, protein sequences, phylogenetic trees, and orthologous groups in the current eggNOG release.

Returns

str JSON string with database statistics.

list_downloadsA

List downloadable data files from the eggNOG 7 database.

Returns a list of all bulk-downloadable files (protein sequences, OG info, phylogenetic trees, taxonomic info, etc.) with their URLs and descriptions.

Returns

str JSON string with download file information.

get_taxid_infoA

Look up taxonomic information for an NCBI taxonomy ID.

Provides guidance on retrieving taxonomic information for a given NCBI taxonomy ID from the eggNOG database. The full taxonomic data is available in the downloadable e7.taxid_info.tsv.gz file.

Parameters

taxid : int NCBI taxonomy ID. Examples: - 9606 (Homo sapiens) - 4932 (Saccharomyces cerevisiae) - 44689 (Danio rerio)

Returns

str JSON string with taxonomic lookup information and download URL.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
version_infoReturn the eggNOG-MCP server version.
database_stats_resourceReturn cached database statistics.
database_downloads_resourceReturn the list of downloadable files.

TDQS

A3.7/5.0

Scored across 10 tools

Disambiguation4/5

Most tools target distinct resources (protein, OG, family, taxid, stats, downloads, search), and descriptions give concrete examples. However, annotate_protein is explicitly a 'convenience wrapper around get_protein' returning overlapping data for the same protein_id, and get_og_content vs get_orthologs/get_protein_family all return species/protein lists with similar shapes, creating mild risk of misselection.

Naming Consistency5/5

Consistent snake_case verb_noun pattern throughout (get_*, list_*, search_*, annotate_*). Minor terminology drift between 'orthologous_group' and 'orthologs' but the convention is clear and predictable.

Tool Count5/5

10 tools is well-scoped for a read-only database API, with each tool covering a distinct lookup or listing need. No bloat and nothing obviously trivial.

Completeness4/5

Core lifecycle is well covered: search, protein annotation, OG detail, OG content, orthologs, family, stats, and downloads. Minor gaps remain (no sequence/FASTA retrieval), and get_taxid_info is effectively a stub that only points to a downloadable file rather than returning the taxonomy data.

Maintenance

ActivityMaintained
ResponsivenessNo issues