Genomics MCP
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GENOMICS_MCP_CONFIG | No | Path to a TOML configuration file. Can be used instead of --config. Example: /path/to/config.toml | |
| GENOMICS_MCP_HTTP_TOKEN | No | Bearer token for HTTP transport. Required when using the HTTP transport (--transport http). Must be at least 32 characters. | |
| GENOMICS_MCP_ALLOWED_ROOTS | No | Allowed root paths for local file access. Set in the environment when running the stdio server. Example: /path/to/your/data |
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 |
|---|---|
| list_sourcesB | List data and reference sources, their state and supported operations. |
| search_datasetsB | Search one archive/catalog for studies or datasets by text query. Available for: ega, ena, encode, geo, ncbi_datasets. |
| describe_datasetA | Describe a study/dataset by native accession, with linked entities. Available for: ega, ena, encode, geo, ncbi_datasets. |
| list_filesA | List files of a study/dataset with format, size, checksums, index and readiness. Available for: ega, ena, encode, geo, local, ncbi_datasets, s3. |
| list_samplesB | List samples of a study/dataset as supplied by the source. Available for: ega, ena, encode, geo, ncbi_datasets. |
| get_sample_metadataA | Get one sample's metadata and phenotype values exactly as supplied by the source. Available for: ega, ena, encode, geo, ncbi_datasets. |
| fetch_fileA | Start a bounded download of a file (and index) to the local work dir. Returns a transfer job; files above the default limit need budget_bytes. Available for: default. |
| get_transfer_statusB | Get progress/result of a transfer started by fetch_file. Available for: default. |
| cancel_transferB | Cancel a running transfer. Available for: default. |
| get_readsB | Alignments overlapping an interval from indexed BAM/CRAM. Flag filters follow samtools -f/-F. CRAM needs a matching reference unless self-contained. Available for: bam, cram. |
| get_coverageB | Read depth over an interval from indexed BAM/CRAM (default excludes UNMAP, SECONDARY, QCFAIL, DUP, like samtools depth). Available for: bam, cram. |
| get_pileupB | Per-position base counts over an interval from indexed BAM/CRAM. Available for: bam, cram. |
| get_variantsB | Variant records and optional genotypes overlapping an interval (VCF/BCF). Available for: bcf, vcf. |
| get_sequenceB | Reference sequence for an interval from an indexed FASTA. Available for: fasta. |
| get_featuresB | Features overlapping an interval from indexed BED/GFF3/GTF or bigBed. Available for: bed, bigbed, gff3, gtf. |
| get_signalB | Signal values or binned summaries over an interval from bigWig. Available for: bigwig. |
| inspect_locusB | Combine data from several files at one locus, plus public evidence. Values derived from private files are only sent to external sources if allow_external_annotation is true. Available for: default. |
| compare_samplesC | Compare genotypes/coverage at an interval across files or samples. Available for: default. |
| resolve_identifierB | Resolve a gene/transcript/protein/variant identifier; reports ambiguity. Available for: default. |
| normalize_variantC | Normalize a variant (VCF-style, HGVS or rsID) on an explicit assembly with a trace. Available for: default. |
| lookup_variantC | Source-attributed evidence for a variant (ClinVar, gnomAD, Ensembl, optional Atlas). No consensus or clinical verdict. Available for: default. |
| lookup_geneC | Gene identifiers, transcripts and source-attributed annotations. Available for: default. |
| lookup_proteinC | Protein identity, function and features from UniProt and cross-references. Available for: default. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| capabilities | Operations implemented in this build, handler keys and planned epics. |
| status | Source states and non-secret configuration summary. |
| schemas | Names of available JSON schemas. |
TDQS
Scored across 23 tools
Each tool targets a distinct data type or action: sequence, features, signal, reads, coverage, pileup, variants, samples, metadata, transfers, locus inspection, sample comparison, identifier resolution, variant normalization, variant/gene/protein lookups, source listing, dataset search/description, and file listing. Overlaps like get_reads/get_coverage/get_pileup are differentiated by output, and resolve_identifier vs lookup_* by scope.
All tool names follow a consistent snake_case verb_noun pattern (e.g., get_sequence, list_samples, fetch_file, normalize_variant, lookup_protein). No mixing of conventions or vague verbs; the pattern is predictable across all 23 tools.
23 tools is slightly above the ideal 3-15 range but reasonable given the breadth of genomics data formats (FASTA, BED, GFF, bigWig, BAM, CRAM, VCF) and operations (access, lookup, transfer, inspection). Each tool appears to earn its place, though some consolidation of similar BAM/CRAM tools could reduce count.
The surface covers core genomics workflows: sequences, features, signal, reads, coverage, pileup, variants, samples, datasets, files, transfers, identifier resolution, variant normalization, and lookups for variants/genes/proteins. Minor gaps exist, such as searching genes by keyword or listing variants by gene without a locus, but agents can work around these.