RepoAI
Browse MCPs

Ensembl Database

88TrustedShips scripts

Gene annotation, ID mapping, and genomic sequence retrieval from the Ensembl REST API.

What it does

Ensembl Database integrates your assistant with the Ensembl genome browser, providing a direct pipeline to core biological data. It transforms your environment into a research-ready station capable of mapping identifiers across various databases and extracting precise genomic sequences or transcript structures without manual browsing.

By installing this, you enable your assistant to handle tasks involving gene annotation and cross-referencing. It manages the complexities of assembly versions and transcript selection automatically, ensuring that the retrieved data follows established biological consensus like MANE Select, while maintaining a clear audit trail of the queries performed.

When it earns its place

Reach for it when…

Use this skill when you need to resolve ambiguous gene symbols to stable IDs, convert between standard formats like UniProt or RefSeq, or extract raw DNA sequences from specific chromosomal coordinates. It is essential for projects requiring consistent, programmatic access to human or model organism genome metadata and variant-related information.

Look elsewhere when…

This skill is not suitable for high-throughput genomic data analysis or running large-scale alignment jobs, as it is designed for targeted queries of specific features. If your task requires complex comparative genomics across hundreds of species simultaneously or deep statistical analysis of variant cohorts, a specialized bioinformatics platform or dedicated pipeline manager will be more efficient.

What to say to use it

You never invoke a skill directly — the assistant picks it up when your request matches what it covers. These are the kinds of things that do that.

  • what is the ENSG identifier for the human TP53 gene
  • fetch the DNA sequence for this genomic region on GRCh37
  • can you map this gene symbol to its UniProt identifier
  • show me the canonical transcript details for this transcript ID

Install it

Install for all your projects

Copy the skill directory into your personal skills folder. Claude picks it up on its own the next time your request matches what it does — there is nothing to enable.

bash
git clone --depth 1 --branch main https://github.com/google-deepmind/science-skills.git /tmp/science-skills
mkdir -p ~/.claude/skills
cp -r /tmp/science-skills/skills/ensembl_database ~/.claude/skills/ensembl-database

Install for one project only

Put it in the project's own skills folder instead, so it can be committed and shared with everyone working on that repository.

bash
cp -r /tmp/science-skills/skills/ensembl_database .claude/skills/ensembl-database

If a skill of the same name exists in both places, the personal one wins.

Installing on Claude.ai or through the API instead? The full guide covers every surface.

Pair it with an MCP server

Ensembl Database changes how the work is done. These servers change what Claude can reach while doing it.

How skills and MCP servers differ →