RepoAI
Browse MCPs

Pubmed Database

88TrustedShips scripts

Scientific literature retrieval and cross-database linking from the NCBI archives.

What it does

Pubmed Database gives your assistant direct access to professional biomedical literature. Instead of guessing based on general training, the model retrieves current clinical data, peer-reviewed abstracts, and research papers directly from official NCBI sources, ensuring the information provided is based on documented evidence.

When it earns its place

Reach for it when…

Best suited for systematic literature reviews, identifying biological associations between proteins or genes and specific papers, and verifying the accuracy of scientific citations or medical terminology in a technical document.

Look elsewhere when…

Avoid using this for broad, non-technical queries that do not require peer-reviewed backing, or for parsing content from non-NCBI journals. It is not designed to perform meta-analyses or synthesize clinical guidelines that exist outside the indexed PubMed archive.

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.

  • find the most recent papers on BRCA1 gene mutations
  • get the abstract for this specific PubMed ID
  • link these chemical compounds to relevant research
  • verify the correct spelling of these medical terms using PubMed

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/pubmed_database ~/.claude/skills/pubmed-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/pubmed_database .claude/skills/pubmed-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

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

How skills and MCP servers differ →