RepoAI
Browse MCPs

Pdb Database

88TrustedShips scripts

Biomolecular structure discovery via automated database interaction.

What it does

Pdb Database integrates direct search and retrieval capabilities for experimentally determined protein and nucleic acid structures. Instead of relying on manual web portal navigation, the assistant executes scripts to query the Protein Data Bank for specific molecular entities, assemblies, or resolution data.

This setup shifts the assistant from providing general textbook knowledge to performing targeted bioinformatic data extraction. It handles schema discovery and API rate management automatically, ensuring that queries for structure similarity or chemical metadata are handled within established usage guidelines.

When it earns its place

Reach for it when…

Use this to perform complex programmatic lookups for specific protein chains, resolution criteria, or primary literature citations when you need to programmatically download or verify structural data for a research workflow.

Look elsewhere when…

This is not intended for high-level textual summaries of broad biological concepts or general literature reviews that do not require access to structural experimental metadata. It is also unsuitable for visualizing 3D molecular models directly.

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 structures of human proteins with a resolution better than 2 angstroms
  • List all entries published in Nature involving this specific ligand
  • Download the PDB file for the protein structure defined by this sequence
  • Find how many structures of this enzyme exist from non-human organisms

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/pdb_database ~/.claude/skills/pdb-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/pdb_database .claude/skills/pdb-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

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

How skills and MCP servers differ →