RepoAI
Browse MCPs

NCBI Sequence Fetch

88TrustedShips scripts

Direct retrieval of protein and nucleotide sequences from NCBI biological databases.

What it does

Ncbi Sequence Fetch enables your assistant to pull biological data directly from NCBI databases. By integrating with Entrez E-utilities, it handles the complex process of identifying and downloading specific sequence records, including protein FASTA files, nucleotide entries, and CDS translations.

Once installed, the assistant moves beyond simple search results by executing precise queries to retrieve raw sequence data. It manages the communication with NCBI servers, providing a structured output that transforms raw database responses into clear, usable information for your research or analysis tasks.

When it earns its place

Reach for it when…

This skill is ideal when you need to programmatically access specific biological sequences using accession numbers, gene names, locus tags, or publication identifiers like PubMed IDs. It serves well for batch retrieval of protein data from patents or verifying genomic information linked to research papers.

Look elsewhere when…

Do not use this for large-scale bioinformatics pipelines or local sequence alignment. It is designed for targeted data retrieval, not for massive genomic analysis or processing entire database dumps, where specialized local software would be more performant and reliable.

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.

  • Fetch the protein sequence for accession NP_001234567
  • Translate the CDS from the nucleotide entry MK034466
  • Find all proteins associated with this PubMed paper
  • Get the sequence for the human BRCA1 gene
  • Extract protein sequences mentioned in this patent

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/ncbi_sequence_fetch ~/.claude/skills/ncbi-sequence-fetch

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/ncbi_sequence_fetch .claude/skills/ncbi-sequence-fetch

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.