Ensembl MCP Server
# Ensembl MCP Server
Model Context Protocol (MCP) server providing access to the Ensembl genomics REST API.
## Features
30+ tools for genomic data access:
- Gene lookup by symbol or ID
- Sequence retrieval
- Genetic variants
- Cross-species homology
- Phenotype data
- Regulatory features
- Ontology and taxonomy data
Full endpoint documentation available in [ENDPOINTS.md](ENDPOINTS.md).
## Installation
### From GitHub
```bash
npm install git+https://github.com/munch-group/ensembl-mcp.git
cd node_modules/ensembl-mcp
npm run build
```
### From source
```bash
git clone https://github.com/munch-group/ensembl-mcp.git
cd ensembl-mcp
npm install
npm run build
```
## Usage with Claude Desktop
```bash
# Using built version
claude mcp add ensembl node /path/to/ensembl-mcp/build/index.js
# Or from npm global install
claude mcp add ensembl npx -y ensembl-mcp
```
## Configuration
Add to your Claude Desktop config:
```json
{
"mcpServers": {
"ensembl": {
"command": "node",
"args": ["/path/to/ensembl-mcp/build/index.js"]
}
}
}
```
## Building
```bash
npm run build
```
## Dependencies
- [@mcp/rest-utils](https://github.com/munch-group/mcp-rest-utils) - Shared REST utilities
- @modelcontextprotocol/sdk - MCP SDK
- zod - Schema validation
## License
ISC
TDQS
Scored across 25 tools
Most tools have distinct purposes, such as get_sequence for sequences and get_homology for homologous genes, but some overlap exists: get_xrefs_by_gene, get_xrefs_by_symbol, and get_xrefs_by_name all handle cross-references with slight variations, which could cause minor confusion. Overall, descriptions clarify boundaries, but the xrefs tools are somewhat redundant.
All tool names follow a consistent verb_noun pattern, primarily using 'get_', 'lookup_', 'map_', 'overlap_', 'search_', and 'vep_' prefixes, with snake_case throughout. This predictability makes it easy for agents to understand and navigate the tool set without naming conflicts.
With 25 tools, the count is borderline high for a genomic data server, feeling slightly heavy but not excessive. It covers various aspects like sequences, variants, and mappings, but could potentially be streamlined by consolidating overlapping tools (e.g., the xrefs group).
The tool set provides comprehensive coverage for genomic and bioinformatics tasks, including data retrieval (e.g., genes, sequences, variants), mapping between coordinates, ontology and taxonomy lookups, and variant prediction with VEP. There are no obvious gaps; it supports full lifecycle operations from search to analysis.