home / mcp / ensembl mcp server
A comprehensive Model Context Protocol (MCP) server that provides access to the Ensembl REST API for genomic data, comparative genomics, and biological annotations.
Configuration
View docs{
"mcpServers": {
"augmented-nature-ensembl-mcp-server": {
"command": "node",
"args": [
"/path/to/ensembl-server/build/index.js"
]
}
}
}You can access Ensembl REST API data for genes, transcripts, sequences, variants, regulatory features, and comparative genomics through a dedicated MCP server. This enables you to query, fetch, and analyze diverse genomic data from Ensembl via a standardized MCP interface, integrated with your MCP client workflows.
Connect to the Ensembl MCP Server using your MCP client. You will interact with a set of named tools that expose Ensembl data through convenient MCP endpoints. Typical tasks include looking up genes, retrieving sequences, finding homologs, predicting variant effects, and mapping coordinates between assemblies. Use the client to invoke tools by their names, supply the required identifiers or regions, and receive structured results that you can integrate into your analyses.
Prerequisites you need on your machine: a modern Node.js environment and npm installed.
1) Build the server locally if you plan to run it as a local MCP server.
2) Start the MCP server as a local stdio server using the runtime command shown in the configuration snippet.
{
"mcpServers": {
"ensembl": {
"type": "stdio",
"name": "ensembl",
"command": "node",
"args": ["/path/to/ensembl-server/build/index.js"]
}
}
}To use the local server with Claude Desktop, you typically build the server, then configure Claude Desktop to point to the local runtime. The provided flow involves building the server and launching it with the node runtime, using the path to the compiled entry point as shown above.
The Ensembl MCP Server exposes a wide range of capabilities, including gene and transcript lookup, sequence retrieval, regulatory feature access, variant data and consequence prediction, comparative genomics, cross-references, and coordinate mapping. You can perform batch queries and fetch data for multiple regions or genes in a single operation.
Get detailed gene information by stable ID or symbol
Retrieve all transcripts for a gene with structural details
Search genes by name, description, or identifier with filtering options
Get DNA sequence for genomic coordinates or gene/transcript ID
Get coding sequence (CDS) for a transcript
Translate DNA sequence to protein sequence
Find orthologous and paralogous genes across species
Get phylogenetic tree for gene family
Get genetic variants in a genomic region
Predict consequences of variants on genes and transcripts
Get regulatory elements in genomic region
Get transcription factor binding motifs in genomic region
Get external database cross-references for genes
Convert coordinates between genome assemblies
Get list of available species and assemblies
Get genome assembly information and statistics
Get chromosome information and karyotype
Look up multiple genes simultaneously
Fetch sequences for multiple regions or features