# Protein Data Bank

> Use this tool when you need to access and analyze protein structure data for research in structural biology. It solves problems related to searching, retrieving, and filtering protein structures, and provides outputs in various formats, including PDB, mmCIF, and XML. The tool is ideal for structural biologists, researchers, and AI applications requiring programmatic access to crystallographic data and molecular structure information.

Canonical page: https://skillsregistry.net/skills/augmented-nature-pdb  
JSON: https://api.skillsregistry.net/v1/skills/augmented-nature-pdb

## Description

This MCP server provides AI assistants with access to the Protein Data Bank (PDB) for structural biology research, built by Augmented Nature using TypeScript and the Model Context Protocol SDK. The implementation offers comprehensive tools for searching protein structures by keyword or UniProt ID, retrieving detailed structure information and coordinates in multiple formats (PDB, mmCIF, XML), downloading structure files with biological assembly support, and accessing structure quality metrics including validation data and refinement statistics. Built with dual API integration using both RCSB PDB's REST API and search services, it supports advanced filtering by experimental method and resolution range, making it valuable for structural biologists analyzing protein structures, researchers conducting comparative structural studies, and AI applications requiring programmatic access to crystallographic data and molecular structure information.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** monitoring
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/augmented-nature-pdb)
- **Repository:** <https://github.com/augmented-nature/pdb-mcp-server>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "augmented-nature-pdb"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/augmented-nature-pdb` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/augmented-nature-pdb/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt