# io.github.cyanheads/ensembl-mcp-server (remote · ensembl.caseyjhand.com)

Look up genes, fetch sequences, predict variant consequences, find orthologs and xrefs via Ensembl.

- Trust score: 71/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `ensembl.caseyjhand.com`: 71/100 (this document), [markdown](https://verifymcp.io/servers/cyanheads-ensembl-mcp-server/ensembl.md), [page](https://verifymcp.io/servers/cyanheads-ensembl-mcp-server/ensembl)
- npm · `@cyanheads/ensembl-mcp-server`: 35/100, [markdown](https://verifymcp.io/servers/cyanheads-ensembl-mcp-server/cyanheads-ensembl-mcp-server.md), [page](https://verifymcp.io/servers/cyanheads-ensembl-mcp-server/cyanheads-ensembl-mcp-server)

## Channel facts

- Endpoint: `https://ensembl.caseyjhand.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.4.2`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 66/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 7 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 79/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 3430 tokens (~214/item across 16 items; 7 tools + 9 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http cyanheads-ensembl-mcp-server https://ensembl.caseyjhand.com/mcp
```

### Codex

```toml
[mcp_servers.cyanheads-ensembl-mcp-server]
url = "https://ensembl.caseyjhand.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "cyanheads-ensembl-mcp-server": {
      "type": "remote",
      "url": "https://ensembl.caseyjhand.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add cyanheads-ensembl-mcp-server --url https://ensembl.caseyjhand.com/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  cyanheads-ensembl-mcp-server:
    url: "https://ensembl.caseyjhand.com/mcp"
```

### Other

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

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 70, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 69, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 67, +1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 66)

First indexed and scored.

## MCP tools (7)

### `ensembl_list_species` (~241 tokens)

List Ensembl 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. Filter by division to select one; use nameContains to find a species by partial name match. With no division, returns the endpoint default division — the vertebrates (~356 species on the default GRCh38 endpoint); pass a division to list that division.

Input parameters:

- `division` (string): Filter to a specific Ensembl division. EnsemblVertebrates includes human, mouse, zebrafish, and other vertebrates. EnsemblPlants covers crop and model plant genomes. EnsemblFungi, EnsemblMetazoa, Ens…
- `nameContains` (string): Case-insensitive substring filter applied locally after fetching. Matches against species name, display name, and common name. Example: "sapiens" matches homo_sapiens; "mouse" matches mus_musculus.

Output parameters:

- `notice` (string): Guidance when the filter matches no species.
- `species` (array): Species matching the filter criteria, sorted by internal name.
- `totalCount` (number): Total number of matching species after local filtering.

### `ensembl_lookup_gene` (~454 tokens)

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). 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 to discover valid species names.

Input parameters:

- `expand_transcripts` (boolean): When true, include the full transcript list in the response. Each transcript has its ID, biotype, canonical flag, and coordinates. Default is false to keep responses compact.
- `id` (string): Ensembl stable gene ID (e.g. ENSG00000139618 or ENSG00000139618.7 with version). Species is not required for ID lookup.
- `ids` (array): Batch lookup: up to 20 Ensembl stable IDs (ENSG…, ENST…). Returns a succeeded/failed split. Provide exactly one of symbol, id, ids, or symbols.
- `species` (string): Species in Ensembl internal format: lowercase scientific name with underscores (e.g. homo_sapiens, mus_musculus, danio_rerio). Optional for symbol lookups — defaults to homo_sapiens; set it for other…
- `symbol` (string): Gene symbol to look up (e.g. BRCA2, TP53, EGFR). Species defaults to homo_sapiens; set species for other organisms. Case-insensitive in most species.
- `symbols` (array): Batch lookup: up to 20 gene symbols. Species defaults to homo_sapiens; set species for other organisms. Returns a succeeded/failed split. Provide exactly one of symbol, id, ids, or symbols.

Output parameters:

- `batch` (object): Batch results. Present for ids or symbols lookups.
- `gene` (object): Single gene record. Present for symbol or id lookups.

### `ensembl_get_sequence` (~504 tokens)

Get Sequence

Fetch the DNA, cDNA, CDS, or protein sequence for a gene, transcript, protein, or genomic region. Returns the sequence with its stable ID, molecule type, and character count — large sequences are returned in full but the length is stated so callers can budget context. 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). 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.

Input parameters:

- `expand_3prime` (integer): Number of base pairs to extend downstream (3' direction) of the requested feature. Default 0. Only applies to genomic sequences and region queries.
- `expand_5prime` (integer): Number of base pairs to extend upstream (5' direction) of the requested feature. Default 0. Only applies to genomic sequences and region queries.
- `id` (string, required): Ensembl stable ID (ENSG…, ENST…, ENSP…) or a genomic region for region mode. Region accepts species:chr:start-end (e.g. homo_sapiens:13:32315086-32400268) or a bare chr:start-end (e.g. 13:32315086-32…
- `species` (string): Species in Ensembl internal format (e.g. homo_sapiens). Required for a bare chr:start-end region; optional for the species:chr:start-end form (the embedded species is used when the field is omitted).…
- `type` (string): Sequence type to retrieve. genomic: full genomic DNA including introns (default). cdna: spliced transcript sequence (requires ENST… ID). cds: coding sequence only, no UTRs (requires ENST… ID with cod…

Output parameters:

- `description` (string): Sequence description from Ensembl, if provided.
- `id` (string): The stable ID or region used for the lookup.
- `length` (number): Sequence length in characters — nucleotides for genomic/cdna/cds, amino-acid residues for protein. Use this to budget context window usage before processing the sequence.
- `seq` (string): The full sequence. DNA sequences use IUPAC nucleotide codes (ACGT + ambiguity codes). Protein sequences use single-letter amino acid codes. Large genomic sequences (e.g. 85 kb for BRCA2) are returned…
- `type` (string): Sequence type returned (genomic, cdna, cds, or protein).

### `ensembl_query_region` (~398 tokens)

Query Genomic 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. 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). 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 to prevent overwhelming returns — requesting variation in an 85 kb region returns 44,000+ entries. Explicitly include variation, regulatory, transcript, or exon only when needed. Exon rows carry the parent transcript ID, so the same exon appears once per transcript it belongs to.

Input parameters:

- `biotype` (string): Optional biotype filter (e.g. protein_coding, lncRNA, SNV). Applied server-side by Ensembl. Not all feature types support biotype filtering.
- `feature` (array): Feature types to retrieve. Default is gene only. Requesting variation in a large region can return tens of thousands of features. Include variation only for targeted small regions (single gene loci o…
- `region` (string, required): Genomic region in chr:start-end format (e.g. 13:32315086-32400268). Ensembl normalizes chromosome names and canonical vertebrate output omits the chr prefix (13, not chr13); a chr-prefixed name like…
- `species` (string, required): Species in Ensembl internal format (e.g. homo_sapiens, mus_musculus). Use ensembl_list_species to discover valid values.

Output parameters:

- `features` (array): Genomic features found in the requested region.
- `notice` (string): Warning or guidance about the result set.
- `region` (string): The region queried, as provided.
- `species` (string): The species queried.
- `totalCount` (number): Number of features returned. Note: very large regions may return truncated results.

### `ensembl_predict_variant` (~671 tokens)

Predict Variant Effect

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.

Input parameters:

- `include_all_colocated_pubmed` (boolean): When true, return every PubMed ID for each colocated variant, overriding max_pubmed_ids_per_variant. Default false to keep responses compact.
- `max_pubmed_ids_per_variant` (integer): Maximum PubMed IDs to return per colocated known variant. Well-studied variants (e.g. rs334) cite 100+ papers; the default trims each list. Set to 0 to return every PubMed ID uncapped. pubmedTotal on…
- `max_transcript_consequences` (integer): Maximum transcript consequences to return per VEP record. High-impact variants can affect 60+ transcripts; the default keeps the response focused on the top consequences. Set to 0 to return every tra…
- `species` (string): Species in Ensembl internal format. Default is homo_sapiens. For non-human variants, set the appropriate species (e.g. mus_musculus for mouse). Use ensembl_list_species to discover valid values.
- `variant` (string, required): Variant in one of three formats: (1) HGVS notation — transcript-relative: ENST00000380152.8:c.2T>A; genomic: 13:g.32316462T>A; (2) Region+allele: chr:start:end:strand/allele — e.g. 1:65568:65568:1/T…

Output parameters:

- `cap` (number): The max_transcript_consequences limit applied.
- `notice` (string): Guidance when no results are returned or when caps omitted detail.
- `results` (array): VEP consequence records — typically one per input variant. Multiple records appear when a single notation matches multiple genomic positions.
- `shown` (number): Total transcript consequences returned across all records after the cap.
- `totalCount` (number): Number of VEP consequence records returned.
- `truncated` (boolean): True when transcript consequences were capped at max_transcript_consequences.

### `ensembl_get_homology` (~428 tokens)

Get Gene Homologs

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.

Input parameters:

- `id` (string): Ensembl stable gene ID (e.g. ENSG00000139618). Use ensembl_lookup_gene to get the stable ID from a symbol. Cannot be combined with symbol.
- `max_results` (integer): Maximum number of homologs to return. Broad orthology queries (e.g. BRCA2 across all species) can return 150+ homologs; the default keeps responses focused. Set to 0 to return every homolog uncapped.…
- `species` (string): Source species (the species the query gene belongs to) in Ensembl internal format. Default is homo_sapiens. Use ensembl_list_species to discover valid values.
- `symbol` (string): Gene symbol in the source species (e.g. BRCA2, TP53). Species defaults to homo_sapiens; set species for other organisms. Cannot be combined with id.
- `target_species` (string): Filter to homologs in a single target species (e.g. mus_musculus for mouse). Omit to return homologs across all available species. Use ensembl_list_species to discover valid values.
- `type` (string): Type of homologs to return. orthologues: genes related by speciation (cross-species equivalents). paralogues: genes related by duplication (within or across species). all: both orthologs and paralogs.

Output parameters:

- `cap` (number): The max_results limit applied to the homolog list.
- `homologs` (array): Homologous genes found for the query gene, capped to max_results. totalCount reports the full count available before the cap.
- `notice` (string): Guidance when no homologs are found or the list was capped.
- `queryId` (string): The resolved Ensembl gene ID used for the homology query.
- `querySpecies` (string): The source species used for the query.
- `queryType` (string): The homology type queried (orthologues, paralogues, or all).
- `shown` (number): Number of homologs returned after the max_results cap.
- `totalCount` (number): Total number of homologs available before the max_results cap. Exceeds the returned homologs count when the list was capped.
- `truncated` (boolean): True when the homolog list was capped at max_results.

### `ensembl_get_xrefs` (~341 tokens)

Get Cross-Database References

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.

Input parameters:

- `dbname` (string): Filter to a specific external database by its Ensembl internal name. Examples: HGNC (HGNC gene ID), Uniprot_gn (UniProt gene name), EntrezGene (NCBI Gene ID), MIM_GENE (OMIM disease gene), RefSeq_mRN…
- `id` (string, required): Ensembl stable gene ID (ENSG…) or transcript ID (ENST…). Use ensembl_lookup_gene to get the stable ID from a gene symbol. xrefs/id returns the full cross-reference set (56+ entries for well-annotated…

Output parameters:

- `notice` (string): Guidance when no cross-references are found.
- `queriedId` (string): The Ensembl stable ID that was queried.
- `totalCount` (number): Total number of cross-references returned.
- `xrefs` (array): Cross-database references for the queried Ensembl ID.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/cyanheads-ensembl-mcp-server/ensembl#diagnostics

## Score history

- 2026-08-03: 71
- 2026-08-02: 71
- 2026-08-01: 70
- 2026-07-31: 70
- 2026-07-30: 69
- 2026-07-29: 68
- 2026-07-28: 68
- 2026-07-27: 67
- 2026-07-26: 66

## Links

- Remote endpoint: https://ensembl.caseyjhand.com/mcp
- Repository: https://github.com/cyanheads/ensembl-mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/cyanheads-ensembl-mcp-server/ensembl/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/cyanheads-ensembl-mcp-server/ensembl/changelog.json
- HTML version of this page: https://verifymcp.io/servers/cyanheads-ensembl-mcp-server/ensembl