ena-biosamples-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| count_recordsB | Count records for a species in the European Nucleotide Archive (ENA, EMBL-EBI). Args: species: Scientific or common name, e.g. "Bos taurus" or "cattle". record_type: "read_run" (sequencing runs), "sample", or "assembly". include_subspecies: Also count subspecies and breeds under this taxon. |
| search_samplesA | Find samples in the European Nucleotide Archive (ENA, EMBL-EBI) for a species. Optionally filter by country of origin. Returns the total number of matching samples plus up to Args: species: Scientific or common name, e.g. "Bos taurus" or "cattle". country: Country name, e.g. "United Kingdom" or "Kenya". Omit for all countries. limit: Max samples to return (1-100). Default 20. include_subspecies: Also include subspecies and breeds under this taxon. |
| get_biosampleA | Get an EMBL-EBI BioSamples record with all its attributes. Attributes include organism, geographic location, tissue, breed and sex where submitted. Args: accession: BioSamples accession, e.g. "SAMEA7658521". Use the accession returned by search_samples. |
| check_sample_metadataA | Check whether an ENA/BioSamples sample's metadata is complete and well-formed. Always checks the fields ENA requires on every sample (organism, collection date, geographic location). Flags fields that are absent, filled with an INSDC missing-value term (e.g. "not collected"), or badly formatted (collection date not ISO 8601). Args: accession: BioSamples accession, e.g. "SAMEA7658521". extra_fields: Additional attributes to require, e.g. ["sex", "breed", "tissue"] for a livestock (FAANG-style) project. |
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 4 tools
count_records and search_samples overlap on the species+samples axis, since search_samples already returns a total count alongside records, which could cause hesitation about which to call for a simple sample tally. Otherwise the retrieval (get_biosample) and validation (check_sample_metadata) tools are clearly distinct despite sharing an accession argument.
All four tools follow a clean verb_noun snake_case pattern (count_records, search_samples, get_biosample, check_sample_metadata) with consistent, predictable verb semantics.
Four tools is on the lean side but coherent for a focused ENA/BioSamples lookup server, covering count, search, fetch, and validate without redundancy. It could arguably support one more retrieval tool, but nothing feels bloated.
The search→get→validate lifecycle for BioSamples is well covered and closure is sensible. Minor gaps: count_records tallies read_run and assembly records but there is no way to retrieve those records, and search_samples only filters by country.