Skip to main content
Glama
rcsb

io.github.rcsb/rcsb-mcp

Official
by rcsb

rcsb_search_by_sequence

Read-onlyIdempotent

Find Protein Data Bank polymer entities matching a given sequence by similarity, using BLAST-like search.

Instructions

Find PDB polymer entities similar to a given sequence (MMseqs2, BLAST-like).

Args: sequence: The query sequence in one-letter code. sequence_type: "protein", "dna", or "rna". identity_cutoff: Minimum sequence identity as a fraction 0-1 (e.g. 0.3 = 30%). evalue_cutoff: Maximum E-value to report. return_type: What to return (default "polymer_entity"); see the "Return types and fetching details" note in the server instructions. limit: Max hits (1-100). Returns polymer_entity IDs like "4HHB_1" — fetch their details with rcsb_get_polymer_entities. 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 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
sort_byNo
all_hitsNo
group_byNo
sequenceYes
attributesNo
return_typeNopolymer_entity
evalue_cutoffNo
sequence_typeNoprotein
sort_directionNoasc
identity_cutoffNo
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?

The description goes well beyond the readOnlyHint/idempotentHint annotations by detailing pagination (next_offset), the all_hits behavior with its 10000-hit refusal and offset incompatibility, facets changing the return shape, grouping semantics, and sort_by restrictions (only SORTABLE attributes, full-text rejection). This extensive operational disclosure gives the agent a clear model of the tool's behavior.

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 15 parameters and complex behaviors. It is front-loaded with a one-line summary, then organized into Args and Returns sections, making it easily scannable. No filler or redundancy.

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?

For a tool of this complexity, the description covers all major behaviors: return value shape, pagination, facets, grouping, sorting constraints, combined attribute filtering, and the all_hits edge case. While it defers to 'server instructions' for faceting/grouping notes, that is appropriate and does not leave the agent without necessary guidance.

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 full responsibility for explaining parameters, and it does so thoroughly. Every parameter is described with types, defaults, constraints, and examples (e.g., identity_cutoff '0.3 = 30%', limit '1-100', sort_by's exclusion of full-text attributes). It also references the AttributeFilter schema for the attributes parameter.

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 'Find PDB polymer entities similar to a given sequence (MMseqs2, BLAST-like)', clearly identifying the tool as a sequence similarity search over PDB polymer entities. This distinguishes it from sibling search tools like rcsb_search_by_structure, rcsb_search_by_chemical, and rcsb_search_by_seqmotif.

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 clearly indicates this is for sequence-based searching and references related tools (rcsb_get_polymer_entities, rcsb_search_by_attribute, rcsb_list_pdb_search_attributes) for follow-up actions. It does not explicitly name alternatives for when not to use this tool, such as rcsb_search_by_seqmotif for short motifs, so it falls short of a perfect 5.

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