Skip to main content
Glama

Rcsb Pdb Search

rcsb_pdb_search
Read-onlyIdempotent

"Find protein structure of [target]" / "search PDB for [protein]" / "is there a crystal structure of [X]" / "[disease target] structures" / "CRISPR / kinase / GPCR structures", text search the RCSB PDB (the global archive of experimentally-determined 3D protein/RNA/DNA structures). Returns matching PDB IDs you can pass to structure or summary. Use for structural biology, drug design, protein characterization.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "CRISPR Cas9"
    },
    "name": "rcsb_pdb_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo1-1000 (default 25).
queryYesFree-text, e.g. "CRISPR Cas9".
return_typeNoentry (default) | polymer_entity | non_polymer_entity | assembly

Output Schema

NameRequiredDescriptionDefault
query_idNo
result_setNo
result_typeNo
total_countNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, idempotent, open-world, non-destructive behavior, so safety needs no restatement. The description adds the important behavioral distinction that this is a free-text search rather than a structured lookup, and that results are IDs intended for chaining. Return-format detail is partly redundant given an output schema exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads intent-matching example queries that map naturally to how an agent phrases requests, then states the action, return, and handoff. The quoted phrase list is somewhat noisy and eats space before the actual verb phrase, but no sentence is truly wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter search tool with full schema coverage, annotations, and an output schema, the description covers purpose, domain, and downstream use adequately. A note on result ordering or paging behavior would close the remaining small gap, but nothing essential is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the schema documents all three parameters including the return_type options and limit range, so the description is not required to compensate. It adds nothing about query syntax, relevance ranking, or when to pick a non-default return_type, leaving it at the baseline for a fully documented schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("text search the RCSB PDB"), defines the archive as experimentally-determined 3D protein/RNA/DNA structures, and names what comes back (matching PDB IDs). The closing sentence routes downstream to `structure` and `summary`, so it is distinguishable from those siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides concrete query phrasings and domain framing ("Use for structural biology, drug design, protein characterization") plus an explicit next-step handoff to `structure`/`summary`. It lacks an explicit when-NOT-to-use clause, e.g., distinguishing a text search from a direct ID lookup, which keeps it below a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.