# io.github.cyanheads/ensembl-mcp-server

> Look up genes, sequences, variants, homologs, and cross-database xrefs from Ensembl REST.

- name: io.github.cyanheads/ensembl-mcp-server
- version: 0.6.1
- connection class: R0 (autonomous)
- trust: 94/100
- quality: 85/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.cyanheads%2Fensembl-mcp-server
- tools: https://api.protogrid.dev/v1/servers/io.github.cyanheads%2Fensembl-mcp-server/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "ensembl-mcp-server": {
      "type": "http",
      "url": "https://ensembl.caseyjhand.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 80
- drivers: +repository +namespace-matches-repo +reachable +uptime-99% +updated-2d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 85/100 (good)

### protocol: 100 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- pass `protocol.list_ttl`: tool list is cacheable (ttlMs 3600000)

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 79 (weight 30)

- pass `tools.descriptions`: every tool has a description
- warn `tools.description_length`: 3 tools have descriptions over 1,024 characters, which crowds the context
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 7 of 7 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: ensembl_lookup_gene (destructiveHint); ensembl_get_sequence (destructiveHint); ensembl_predict_variant (destructiveHint); …
- pass `tools.token_cost`: about 5,517 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 75 (weight 15)

- warn `stability.changes`: 19 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: deps.dev does not know @cyanheads/ensembl-mcp-server@0.6.1, @cyanheads/ensembl-mcp-server@0.6.1

- tools: 7, about 5,517 tokens to load them all
- tool set hash: 8fcfdbccee5bfc444b1d564d190fa72b
- tools last changed: 2026-10-19T03:49:15.576Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.cyanheads/ensembl-mcp-server.svg)](https://protogrid.dev/servers/io.github.cyanheads/ensembl-mcp-server)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-19 `ensembl_get_xrefs` changed (description, inputSchema, outputSchema)
  - before: Retrieve cross-database references for a gene or feature — HGNC, UniProt, EntrezGene, OMIM, RefSeq, Reactome, and others. Returns each xref with its database name, primary ID, display ID, and description. The dbname filter narrows to specific databases; omit to return all xrefs. IDs returned here chain to protein (pubchem via UniProt), literature (pubmed via PubMed IDs), disease (OMIM via MIM_GENE), and pathway (Reactome) resources. Requires an Ensembl stable ID — use ensembl_lookup_gene to get the ENSG… ID first. Common dbname values: HGNC, Uniprot_gn, EntrezGene, MIM_GENE, RefSeq_mRNA, RefSeq_peptide, Reactome, GO (Gene Ontology), ChEMBL.
  - after: Retrieve cross-database references for a gene or feature — HGNC, UniProt, EntrezGene, OMIM, RefSeq, Reactome, and others. Returns each xref with its database name, primary ID, display ID, and description. By default only the requested object level is queried; all_levels=true includes transcript and translation references for a gene. The dbname filter narrows this scope. IDs returned here chain to protein (pubchem via UniProt), literature (pubmed via PubMed IDs), disease (OMIM via MIM_GENE), and pathway (Reactome) resources. Requires an Ensembl stable ID — use ensembl_lookup_gene to get the ENSG… ID first. Common dbname values: HGNC, Uniprot_gn, EntrezGene, MIM_GENE, RefSeq_mRNA, RefSeq_peptide, Reactome_gene (gene pathways), Reactome (translation pathways), GO (Gene Ontology), ChEMBL.
- 2026-10-19 `ensembl_get_homology` changed (description, outputSchema)
  - before: Find orthologs and/or paralogs of a gene across species. Returns each homolog's stable ID, species, homology type (ortholog_one2one, ortholog_one2many, paralog_many2many, etc.), perc_id (percent identity), perc_pos (percent positives), and taxonomy level. Essential for cross-species research — for example, "what is the mouse equivalent of human TP53?" or "how conserved is BRCA2 across mammals?". Provide either symbol + species or a stable gene ID. Target species can be filtered to a single species or left open to return all available homologs.
  - after: Find orthologs and/or paralogs of a gene across species. Returns each homolog's stable ID, species, homology type (ortholog_one2one, ortholog_one2many, paralog_many2many, etc.), percId (percent identity), percPos (percent positives), and taxonomy level. Essential for cross-species research — for example, "what is the mouse equivalent of human TP53?" or "how conserved is BRCA2 across mammals?". Provide either symbol + species or a stable gene ID. Target species can be filtered to a single species or left open to return all available homologs. Includes targetProteinId when available for ensembl_get_sequence with type="protein". targetSymbol is best-effort: a secondary gene lookup shares five seconds across the returned rows and the remaining call deadline; missing names never remove homologs.
- 2026-10-19 `ensembl_predict_variant` changed (outputSchema)
- 2026-10-19 `ensembl_query_region` changed (inputSchema)
- 2026-10-19 `ensembl_get_sequence` changed (description)
  - before: Fetch the DNA, cDNA, CDS, or protein sequence for a gene, transcript, protein, or genomic region. Returns a window of the sequence — the first 10,000 characters by default — with its stable ID, molecule type, and full length. When more follows the window, truncated is true and nextOffset is the offset to request next; walking nextOffset reconstructs the whole sequence, and max_length 0 returns everything from offset to the end. The type parameter selects which sequence is fetched: genomic (default, includes introns), cdna (spliced transcript), cds (coding sequence only), protein. For region mode, set id to a region — either species:chr:start-end (e.g. homo_sapiens:13:32315086-32400268) or a bare chr:start-end with species set (e.g. id 13:32315086-32400268, species homo_sapiens), spanning at most 10,000,000 bases; a :-1 suffix (13:32315086-32315100:-1) returns the reverse-strand sequence. Regions return genomic DNA only. Protein sequences require a transcript or protein stable ID (ENST…/ENSP…), not a gene ID — use ensembl_lookup_gene with expand_transcripts=true to get the canonical transcript ID first.
  - after: Fetch the DNA, cDNA, CDS, or protein sequence for a gene, transcript, protein, or genomic region. Returns a window of the sequence — the first 10,000 characters by default — with its stable ID, molecule type, and full length. When more follows the window, truncated is true and nextOffset is the offset to request next; walking nextOffset reconstructs the whole sequence, and max_length 0 returns everything from offset to the end. The type parameter selects which sequence is fetched: genomic (default, includes introns), cdna (spliced transcript), cds (coding sequence only), protein. For region mode, set id to a region — either species:chr:start-end (e.g. homo_sapiens:13:32315086-32400268) or a bare chr:start-end with species set (e.g. id 13:32315086-32400268, species homo_sapiens), spanning at most 10,000,000 bases; a :-1 suffix (13:32315086-32315100:-1) returns the reverse-strand sequence. Regions return genomic DNA only. Protein sequences require a transcript or protein stable ID (ENST…/ENSP…), not a gene ID — use ensembl_lookup_gene and its canonicalTranscript field first; expand_transcripts=true also supplies transcript biotypes and MANE Select accessions.
- 2026-10-19 `ensembl_lookup_gene` changed (description, inputSchema, outputSchema)
  - before: Resolve a gene by symbol + species (or by stable ID) to its Ensembl ID, genomic location (chr:start-end:strand), biotype, description, and transcript list. Entry point for most workflows — the stable ID and coordinates returned here are inputs to other tools. Accepts both symbol lookup (BRCA2 + homo_sapiens) and direct ID lookup (ENSG00000139618). A symbol that is not a current gene name is matched against synonyms and former symbols (HER2 → ERBB2), reported as matchedAlias; when it maps to several genes the result is ambiguous, listing the candidates to retry by id. Supports batch lookup of up to 20 IDs or symbols in one call via the ids or symbols field. Provide exactly one of symbol, id, ids, or symbols. For symbol lookups species defaults to homo_sapiens (override for other organisms); for ID lookups species is not needed. Use ensembl_list_species with nameContains (a genus or common name) to find valid species names.
  - after: Resolve a gene by symbol + species (or by stable ID) to its Ensembl ID, genomic location (chr:start-end:strand), biotype, description, and transcript list. Entry point for most workflows — the stable ID and coordinates returned here are inputs to other tools. Accepts both symbol lookup (BRCA2 + homo_sapiens) and direct ID lookup (ENSG00000139618). A symbol that is not a current gene name is matched against synonyms and former symbols (HER2 → ERBB2), reported as matchedAlias; when it maps to several genes the result is ambiguous, listing the candidates to retry by id. Supports batch submission of up to 1,000 IDs or symbols: the first 20 distinct queries are resolved, and batch.omitted names the unattempted remainder to resubmit. Provide exactly one of symbol, id, ids, or symbols. For symbol lookups species defaults to homo_sapiens (override for other organisms); for ID lookups species is not needed. Use ensembl_list_species with nameContains (a genus or common name) to find valid species names.
- 2026-10-14 `ensembl_get_xrefs` changed (inputSchema, outputSchema)
- 2026-10-14 `ensembl_get_homology` changed (inputSchema, outputSchema)
- 2026-10-14 `ensembl_predict_variant` changed (inputSchema, outputSchema)
- 2026-10-14 `ensembl_query_region` changed (description, inputSchema, outputSchema)
  - before: Find genomic features overlapping a chromosomal region: genes, transcripts, variants, regulatory elements, or exons. Returns each feature with its stable ID, type, location, biotype, and name, plus the genome assembly the coordinates are on. Useful for "what's in this locus?" and for seeding follow-up lookups. Region format is chr:start-end (e.g. 13:32315086-32400268 for the BRCA2 locus), spanning at most 5,000,000 bases. Ensembl normalizes chromosome names and canonical vertebrate output omits the chr prefix (13, not chr13); a chr-prefixed name like chr13 is also accepted. The feature parameter defaults to gene only — requesting variation in an 85 kb region matches 44,000+ entries. Explicitly include variation, regulatory, transcript, or exon only when needed. The response returns up to max_results features (default 100) while totalCount always reports the full count; set max_results to 0 for every feature, or query a smaller region to see a different slice. Exon rows carry the parent transcript ID, so the same exon appears once per transcript it belongs to.
  - after: Find genomic features overlapping a chromosomal region: genes, transcripts, variants, regulatory elements, or exons. Returns each feature with its stable ID, type, location, biotype, and name, plus the genome assembly the coordinates are on. Useful for "what's in this locus?" and for seeding follow-up lookups. Region format is chr:start-end with species set (e.g. 13:32315086-32400268 for the BRCA2 locus), or species:chr:start-end (e.g. homo_sapiens:13:32315086-32400268), spanning at most 5,000,000 bases. Ensembl normalizes chromosome names and canonical vertebrate output omits the chr prefix (13, not chr13); a chr-prefixed name like chr13 is also accepted. The feature parameter defaults to gene only — requesting variation in an 85 kb region matches 44,000+ entries. Explicitly include variation, regulatory, transcript, or exon only when needed. The response returns up to max_results features (default 100) while totalCount always reports the full count; set max_results to 0 for every feature, or query a smaller region to see a different slice. Exon rows carry the parent transcript ID, so the same exon appears once per transcript it belongs to.

Full history: https://api.protogrid.dev/v1/servers/io.github.cyanheads%2Fensembl-mcp-server/changes

## Dependencies

- npm @cyanheads/ensembl-mcp-server@0.6.1: unknown
- npm @cyanheads/ensembl-mcp-server@0.6.1: unknown

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://ensembl.caseyjhand.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.99159664)

## Packages

- npm @cyanheads/ensembl-mcp-server@0.6.1
- npm @cyanheads/ensembl-mcp-server@0.6.1

## Tools (7)

- `ensembl_get_homology`: Find orthologs and/or paralogs of a gene across species. Returns each homolog's stable ID, species, homology type (ortholog_one2one, ortholog_one2many, paralog_many2many, etc.), percId (percent identity), percPos (percent positives), and taxonomy level. Essential for cross-species research — for example, "what is the mouse equivalent of human TP53?" or "how conserved is BRCA2 across mammals?". Provide either symbol + species or a stable gene ID. Target species can be filtered to a single species or left open to return all available homologs. Includes targetProteinId when available for ensembl_get_sequence with type="protein". targetSymbol is best-effort: a secondary gene lookup shares five seconds across the returned rows and the remaining call deadline; missing names never remove homologs.
- `ensembl_get_sequence`: Fetch the DNA, cDNA, CDS, or protein sequence for a gene, transcript, protein, or genomic region. Returns a window of the sequence — the first 10,000 characters by default — with its stable ID, molecule type, and full length. When more follows the window, truncated is true and nextOffset is the offset to request next; walking nextOffset reconstructs the whole sequence, and max_length 0 returns everything from offset to the end. The type parameter selects which sequence is fetched: genomic (default, includes introns), cdna (spliced transcript), cds (coding sequence only), protein. For region mode, set id to a region — either species:chr:start-end (e.g. homo_sapiens:13:32315086-32400268) or a bare chr:start-end with species set (e.g. id 13:32315086-32400268, species homo_sapiens), spanning at most 10,000,000 bases; a :-1 suffix (13:32315086-32315100:-1) returns the reverse-strand sequence. Regions return genomic DNA only. Protein sequences require a transcript or protein stable ID (ENST…/ENSP…), not a gene ID — use ensembl_lookup_gene and its canonicalTranscript field first; expand_transcripts=true also supplies transcript biotypes and MANE Select accessions.
- `ensembl_get_xrefs`: Retrieve cross-database references for a gene or feature — HGNC, UniProt, EntrezGene, OMIM, RefSeq, Reactome, and others. Returns each xref with its database name, primary ID, display ID, and description. By default only the requested object level is queried; all_levels=true includes transcript and translation references for a gene. The dbname filter narrows this scope. IDs returned here chain to protein (pubchem via UniProt), literature (pubmed via PubMed IDs), disease (OMIM via MIM_GENE), and pathway (Reactome) resources. Requires an Ensembl stable ID — use ensembl_lookup_gene to get the ENSG… ID first. Common dbname values: HGNC, Uniprot_gn, EntrezGene, MIM_GENE, RefSeq_mRNA, RefSeq_peptide, Reactome_gene (gene pathways), Reactome (translation pathways), GO (Gene Ontology), ChEMBL.
- `ensembl_list_species`: List species supported by Ensembl with display name, common name, assembly, taxon ID, and division. Required discovery step — species names like homo_sapiens are opaque to non-biologists and are the input format every other Ensembl tool expects. Use nameContains to find a species by partial name match; filter by division to select one. With no division, lists the endpoint default division — the vertebrates (~356 species on the default GRCh38 endpoint). Species are sorted by internal name and returned max_results at a time (default 50); totalCount reports every match, and when more follow, nextOffset is the offset for the next page.
- `ensembl_lookup_gene`: Resolve a gene by symbol + species (or by stable ID) to its Ensembl ID, genomic location (chr:start-end:strand), biotype, description, and transcript list. Entry point for most workflows — the stable ID and coordinates returned here are inputs to other tools. Accepts both symbol lookup (BRCA2 + homo_sapiens) and direct ID lookup (ENSG00000139618). A symbol that is not a current gene name is matched against synonyms and former symbols (HER2 → ERBB2), reported as matchedAlias; when it maps to several genes the result is ambiguous, listing the candidates to retry by id. Supports batch submission of up to 1,000 IDs or symbols: the first 20 distinct queries are resolved, and batch.omitted names the unattempted remainder to resubmit. Provide exactly one of symbol, id, ids, or symbols. For symbol lookups species defaults to homo_sapiens (override for other organisms); for ID lookups species is not needed. Use ensembl_list_species with nameContains (a genus or common name) to find valid species names.
- `ensembl_predict_variant`: Predict the functional consequences of a sequence variant using the Ensembl Variant Effect Predictor (VEP). Accepts three input formats: HGVS notation (transcript-relative, e.g. ENST00000380152.8:c.2T>A, or genomic, e.g. 13:g.32316462T>A); region+allele (chr:start:end:strand/allele, e.g. 1:65568:65568:1/T); and a dbSNP rsID (e.g. rs334). Returns the most severe consequence term, affected transcripts and genes, impact level (HIGH/MODERATE/LOW/MODIFIER), and any colocated known variants with clinical significance. HGVS input: provide the full notation including transcript version for best results. Region+allele input: Ensembl normalizes chromosome names and canonical vertebrate output omits the chr prefix (a chr-prefixed name is also accepted). By default the response caps transcript consequences (max_transcript_consequences) and per-variant PubMed IDs (max_pubmed_ids_per_variant) to keep large VEP results compact — well-studied variants like rs334 otherwise carry 60+ consequences and 100+ citations. Truthful totals are always reported; set a cap to 0 (or include_all_colocated_pubmed=true) to retrieve the full set.
- `ensembl_query_region`: Find genomic features overlapping a chromosomal region: genes, transcripts, variants, regulatory elements, or exons. Returns each feature with its stable ID, type, location, biotype, and name, plus the genome assembly the coordinates are on. Useful for "what's in this locus?" and for seeding follow-up lookups. Region format is chr:start-end with species set (e.g. 13:32315086-32400268 for the BRCA2 locus), or species:chr:start-end (e.g. homo_sapiens:13:32315086-32400268), spanning at most 5,000,000 bases. Ensembl normalizes chromosome names and canonical vertebrate output omits the chr prefix (13, not chr13); a chr-prefixed name like chr13 is also accepted. The feature parameter defaults to gene only — requesting variation in an 85 kb region matches 44,000+ entries. Explicitly include variation, regulatory, transcript, or exon only when needed. The response returns up to max_results features (default 100) while totalCount always reports the full count; set max_results to 0 for every feature, or query a smaller region to see a different slice. Exon rows carry the parent transcript ID, so the same exon appears once per transcript it belongs to.