RepoAI
Browse MCPs

UniProt Database

88TrustedShips scripts

Retrieval of protein metadata, functional annotations, and sequence records from UniProt.

What it does

Integrating this skill equips your assistant with a dedicated interface for querying the UniProt ecosystem. It shifts the assistant from relying on general internal knowledge to fetching verified, up-to-date data directly from UniProtKB, UniParc, and UniRef, ensuring higher accuracy for biological research tasks.

This skill automates the connection to official protein databases, allowing for structured data retrieval rather than manual web searches. It includes specialized tools for ID mapping, batch metadata downloads, and historical record tracking, making it a primary resource for bioinformatics workflows.

When it earns its place

Reach for it when…

Apply this when your work involves identifying protein functions, linking genes to specific organisms, or mapping protein identifiers across different biological databases. It is particularly effective for generating lists of protein attributes or verifying details about a particular accession number found in scientific literature.

Look elsewhere when…

Do not attempt to use this for computational biology tasks such as calculating protein folding structures, performing multiple sequence alignments, or running similarity searches between sequences. These operations require specialized bioinformatics software that this database access tool does not provide.

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.

  • Look up the primary function of the protein with this UniProt accession number.
  • Can you map these gene identifiers to UniProt entry IDs?
  • Find all human proteins associated with this specific cellular pathway.
  • Retrieve the sequence data for these entries in a batch format.

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/uniprot_database ~/.claude/skills/uniprot-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/uniprot_database .claude/skills/uniprot-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

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

How skills and MCP servers differ →