Skip to main content
Glama
rcsb

io.github.rcsb/rcsb-mcp

Official
by rcsb

rcsb_search_by_structure

Read-onlyIdempotent

Search the Protein Data Bank for structures with a 3D shape similar to a reference PDB entry, with optional filters and grouping.

Instructions

Find structures with a similar 3D shape to a reference PDB structure.

Args: entry_id: Reference PDB entry, e.g. "4HHB". assembly_id: Use this biological assembly as the reference (e.g. "1"). Defaults to assembly "1" when neither assembly_id nor asym_id is given. asym_id: Use this single chain as the reference instead (mutually exclusive with assembly_id). return_type: What to return (defaults to "assembly" for an assembly reference or "polymer_instance" for a chain reference); see the "Return types and fetching details" note in the server instructions. limit: Max hits (1-100). offset: Number of hits to skip, for paging; pass the response's next_offset back with the same query to fetch the next page. all_hits: Return the COMPLETE result set in one call (for an explicit "ALL ..." request); ignores limit, can't be combined with offset, and is refused above 10000 hits. Ignored when facets is set. attributes: Optional structured filters AND/OR-combined with this match — a list of AttributeFilter {attribute, operator, value, negation?, case_sensitive?} (e.g. restrict to an organism or resolution). See rcsb_search_by_attribute / rcsb_list_pdb_search_attributes for paths and operators. logical_operator: Combine this match and the attribute conditions with "and" (default) or "or". facets: Optional aggregation specs to return a breakdown / distribution instead of hits (see the faceting note in the server instructions for the spec). group_by, group_by_ranking: Collapse redundant polymer_entity hits into clusters, one representative each (needs return_type="polymer_entity") — see the grouping note in the server instructions. sort_by: Attribute path to order the hits by, replacing the default shape-similarity ordering (each hit's score is still returned); omit to keep it. Only SORTABLE attributes work: those listing exact_match (strings) or equals (numbers/dates) in rcsb_list_pdb_search_attributes; full-text-only attributes (e.g. struct.title) and return_type="mol_definition" are rejected. sort_direction: "asc" (default) or "desc"; applies only when sort_by is set.

Returns: {total_count, returned, offset, has_more, next_offset, hits:[{id, score}], editor}; with facets, instead returns {total_count, facets, editor}.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo
facetsNo
offsetNo
asym_idNo
sort_byNo
all_hitsNo
entry_idYes
group_byNo
attributesNo
assembly_idNo
return_typeNo
sort_directionNoasc
group_by_rankingNo
logical_operatorNoand

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior5/5

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

Even with annotations (readOnlyHint, idempotentHint, etc.), the description adds substantial behavioral detail: defaults for assembly/asym_id, mutual exclusivity, pagination via next_offset, all_hits constraints, ignoring facets, sort_by limitations, and the exact return format. It also flags edge cases such as refusing all_hits above 10000 and rejecting mol_definition for sort_by, making behavior fully transparent.

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

Conciseness5/5

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

The description is long but every sentence earns its place given 14 parameters. It is front-loaded with a single-sentence purpose, then organized into Args and Returns sections with clear formatting, and references external notes for advanced facets/grouping to avoid unnecessary bloat. This is appropriately concise for the tool's complexity.

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

Completeness5/5

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

The description completely covers the tool's context: input details, defaults, mutually exclusive options, output structure (including facets alternative), pagination, sorting constraints, and references to related tools and server instructions. With an output schema present, it does not need to restate return types, but it still explains the shape of the result. No gaps are evident.

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

Parameters5/5

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

With 0% schema description coverage, the description carries the full burden and succeeds. Each parameter is explained beyond its name/title: entry_id gets an example, assembly_id/asym_id get mutual exclusivity and default behavior, limit/offset get ranges and pagination semantics, attributes get a nested filter structure example, and sort_by gets constraints. This fully compensates for the sparse 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?

The description opens with a specific verb+resource: 'Find structures with a similar 3D shape to a reference PDB structure.' This clearly distinguishes it from sibling search tools like rcsb_search_by_sequence, rcsb_search_by_chemical, and rcsb_search_by_attribute by uniquely focusing on 3D shape similarity.

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?

The description gives clear context for when to use the tool (given a reference PDB structure for 3D shape similarity) and references alternatives for attribute filtering (rcsb_search_by_attribute). It does not explicitly state when NOT to use it (e.g., vs. sequence or chemical search), so it misses the top score.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/rcsb/rcsb-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server