Tools

Seven tools covering the core Ensembl REST API surface — species discovery, gene/transcript lookup, sequence retrieval, genomic region overlap, variant consequence prediction, cross-species homology, and external database cross-references:

ensembl_list_species

Discovery tool for the Ensembl species catalog.

• Filter by division: vertebrates, plants, fungi, metazoa, or protists
• Optional name filter (nameContains) for local substring matching
• Returns display name, common name, assembly, taxon ID, and Ensembl division for each species
• Required first step — species names like homo_sapiens are opaque to non-biologists and are the input format every other tool expects

ensembl_lookup_gene

Single entry point for resolving gene identity.

• Symbol + species lookup (BRCA2 + homo_sapiens) or direct stable ID lookup (ENSG00000139618)
• Batch lookup of up to 20 IDs or symbols in one call via POST endpoints
• Optional transcript expansion — returns full transcript list with biotype and canonical flag
• Returns Ensembl stable ID, genomic location (chr:start-end:strand), biotype, description, and transcript list
• Errors: not_found (symbol or ID not in Ensembl), invalid_species (call ensembl_list_species to discover valid names)

ensembl_get_sequence

Fetch any sequence type for any Ensembl feature.

• Molecule types: genomic (default, includes introns), cdna (spliced), cds (coding only), protein
• Accepts stable IDs or species:chr:start-end region format for genomic region mode
• Optional flanking sequence (expand_5prime, expand_3prime) in base pairs
• Returns sequence with stable ID, molecule type, and character count — large sequences (e.g. BRCA2 at 85,183 bp genomic) returned in full with explicit length so callers can budget context usage

ensembl_query_region

Find all genomic features overlapping a chromosomal window.

• Region format: chr:start-end (e.g. 13:32315086-32400268) — no chr prefix for vertebrates
• Feature types: gene (default), transcript, variation, regulatory, exon
• Optional biotype filter
• Defaults to gene only to prevent context overload — a large locus can contain 44,000+ variants when all feature types are selected

ensembl_predict_variant

Predict variant consequences via the Ensembl VEP.

• Accepts HGVS notation (transcript-relative: ENST00000380152.8:c.2T>A) or genomic region+allele format (13:32316462:32316462:1/A)
• Returns most severe consequence term, affected transcripts and genes, impact level (HIGH/MODERATE/LOW/MODIFIER)
• Includes colocated known variants with clinical significance (ClinVar, dbSNP)
• Errors: invalid_notation (check format), not_found (location outside any known transcript)

ensembl_get_homology

Cross-species homolog lookup.

• Returns orthologs (default) or paralogs, or both
• Optional target_species filter to narrow to specific organisms
• Each homolog carries stable ID, species, relationship type (ortholog_one2one, ortholog_one2many, etc.), perc_id, perc_pos, and taxonomy level

ensembl_get_xrefs

Full cross-database reference set for any Ensembl feature.

• Returns all external IDs by default: HGNC, UniProt, EntrezGene, OMIM, RefSeq, Reactome, and more (56 xrefs for BRCA2)
• Optional dbname filter (e.g. HGNC, Uniprot_gn, EntrezGene, MIM_GENE) to narrow output
• Uses the xrefs/id endpoint (not xrefs/symbol) — returns the full cross-reference set
• IDs returned here chain directly to protein, literature, disease, and pathway resources in other MCP servers

Resources and prompts

All resource data is also reachable via tools. ensembl://species returns the endpoint default division (vertebrates) and ensembl://species/{division} returns a named division; ensembl_list_species is the tool equivalent, filtering by division and name.

Features

Built on @cyanheads/mcp-ts-core:

• Declarative tool, resource, and prompt definitions — single file per primitive, framework handles registration and validation
• Unified error handling — handlers throw, framework catches, classifies, and formats
• Pluggable auth: none, jwt, oauth
• Swappable storage backends: in-memory, filesystem, Supabase, Cloudflare KV/R2/D1
• Structured logging with optional OpenTelemetry tracing
• STDIO and Streamable HTTP transports

Ensembl-specific:

• Keyless REST API — no API key required; Ensembl REST is fully public at 55,000 req/hr
• Rate-limit-aware service layer: tracks x-ratelimit-remaining, retries 429 with Retry-After, and retries transient 5xx
• Batch POST endpoints used throughout — POST /lookup/id (up to 50 IDs) and POST /lookup/symbol/{species} reduce N+1 round trips in multi-gene workflows
• GRCh37 legacy support via ENSEMBL_BASE_URL — point the entire server at https://grch37.rest.ensembl.org for clinical workflows on the older assembly
• All coordinate-bearing responses echo the assembly name so agents never see a bare genomic position without assembly context

Agent-friendly output:

• Sequence character count stated on every ensembl_get_sequence response so callers can budget context before consuming large genomic sequences
• ensembl_list_species is explicitly the discovery step — tool descriptions call out the opaque internal-name format and direct agents to it before using species-dependent tools
• Cross-tool chaining made explicit: xref IDs from ensembl_get_xrefs are described as inputs for protein and literature servers; the ensembl_gene_dossier prompt sequences the full 7-tool research workflow

Getting started

Public Hosted Instance

A public instance is available at https://ensembl.caseyjhand.com/mcp — no installation required. Point any MCP client at it via Streamable HTTP:

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

Self-Hosted / Local

Add the following to your MCP client configuration file.

{
  "mcpServers": {
    "ensembl-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/ensembl-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with npx (no Bun required):

{
  "mcpServers": {
    "ensembl-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/ensembl-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with Docker:

{
  "mcpServers": {
    "ensembl-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "MCP_TRANSPORT_TYPE=stdio",
        "ghcr.io/cyanheads/ensembl-mcp-server:latest"
      ]
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcp

Prerequisites

• Bun v1.4.0 or higher (or Node.js v24+).
• No API key required — Ensembl REST is fully public.

Installation

1. Clone the repository:

git clone https://github.com/cyanheads/ensembl-mcp-server.git

2. Navigate into the directory:

cd ensembl-mcp-server

3. Install dependencies:

bun install

4. Configure environment:

cp .env.example .env
# edit .env if you need to override ENSEMBL_BASE_URL (e.g. for GRCh37)

Configuration

All configuration is validated at startup via Zod schemas in src/config/server-config.ts.

See .env.example for the full list of optional overrides.

Running the server

Local development

• Build and run:

  sh

  Copy

  # One-time build
  bun run rebuild
  
  # Run the built server
  bun run start:stdio
  # or
  bun run start:http
  

• Run checks and tests:

  sh

  Copy

  bun run devcheck   # Lint, format, typecheck, security
  bun run test       # Vitest test suite
  bun run lint:mcp   # Validate MCP definitions against spec
  

Docker

docker build -t ensembl-mcp-server .
docker run --rm -p 3010:3010 ensembl-mcp-server

The Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/ensembl-mcp-server. OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.

Project structure

Development guide

See CLAUDE.md for development guidelines and architectural rules. The short version:

• Handlers throw, framework catches — no try/catch in tool logic
• Use ctx.log for request-scoped logging, ctx.state for tenant-scoped storage
• Register new tools and resources in the createApp() arrays in src/index.ts
• Wrap external API calls: validate raw → normalize to domain type → return output schema; never fabricate missing fields

Contributing

Issues and pull requests are welcome. Run checks and tests before submitting:

bun run devcheck
bun run test

License

Apache-2.0 — see LICENSE for details.