io.github.cyanheads/interpro-mcp-server

Find UniProt proteins carrying an InterPro or member signature. Defaults to reviewed human proteins; reviewedOnly=false includes all review statuses in the chosen taxon. Optional isFragment filters fragment annotations; false does not prove sequence completeness. architectureId intersects the provider Pfam grouping with these selections, without implying functional equivalence; metadata-only hits disclose unavailable entry and taxon details without per-protein requests. proteomeId intersects one UniProt proteome, such as protein.proteome from interpro_get_protein_domains, with every selection including taxonId.

Retrieve a Pfam, CDD, or PIRSF clan/set and a cursor page of member entries; optionally include its relationship graph, returned in slices that fit the response budget and paged with relationshipOffset.

Retrieve one InterPro or member-database entry with full metadata by default. Select optional sections while retaining core and unknown metadata, or supply overlapLimit to page whole overlap records in upstream order; offsets are not a snapshot across calls.

Retrieve InterPro and member-signature matches on a canonical UniProt protein, preserving every location and discontinuous fragment. Optionally select records covering a residue, include extra predicted features, and include functional residue rules with provenance. Budgeted segments hold whole records in order: matches, requested extras, then requested residue rules sorted by key. The first segment carries protein metadata; continue coverage.nextCursor until hasMore is false.

Check an InterProScan job started by interpro_scan_sequence, waiting up to waitSeconds for it to finish. Returns the matches once finished, otherwise its queued or running status to check again later. Matches are InterProScan records verbatim, 1-based and inclusive, with the InterPro and InterProScan versions that produced them. Jobs and their results expire seven days after submission.

Retrieve InterPro and member-signature matches on one PDB entry's protein chains. Each chain record keeps match locations in chain numbering (1-based start/end beside author auth_start/auth_end, which can be null), in UniProt numbering, and the chain-to-UniProt residue map, with discontinuous fragments preserved; the UniProt protein is null for unmapped chains. InterPro nests at most 20 chain records per match; set chain to read one chain completely. Budgeted segments hold whole matches; the first carries structure metadata listing the protein chains. Continue coverage.nextCursor until hasMore is false.

List supported InterPro database slugs, entry types, accession and PDB identifier patterns, common taxon IDs, or current release information.

Find InterPro domain, family, and site matches for one raw protein sequence that has no UniProt accession. Sequences already in UniParc return precalculated matches at once; any other sequence starts one InterProScan 6 job, which commonly runs about ten minutes, so the usual first result is a jobId to read with interpro_get_scan_result. Repeating a sequence whose job is still running returns the same jobId instead of starting another. Matches are InterProScan records verbatim, 1-based and inclusive, each naming its member database and release.

Search InterPro entries or member signatures by text or entry type. GO filters require sourceDatabase interpro; integratedInto selects member signatures for an InterPro accession. Results are cursor-paged; use interpro_get_entry for full metadata.