uniprot_get_evidence_summary
Aggregate ECO codes (Evidence and Conclusion Ontology) across an entry and grade them into a 0-100 evidence-confidence score (high / moderate / low / very-low). Distinguishes wet-lab confirmed from inferred-by-similarity from automatic.
How to use it
Project documentation lists uniprot_get_evidence_summary for the Uniprot MCP MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), then check which tools your installed version makes available. Tool availability can depend on configuration and credentials. A server handshake does not verify this tool’s behavior. See the full listing for setup details.
Install Uniprot MCP
uvx uniprot-mcp-serverOther tools in Uniprot MCP (39)
Up to 100 entries in one call; invalid accessions filtered client-side.
Derived sequence chemistry from the FASTA: MW / pI / GRAVY / aromaticity / charge / ε₂₈₀.
Every feature overlapping a residue position. Critical for variant-effect interpretation.
Catalytic and ligand-binding residues: active sites, binding sites, sites, metal binding, DNA binding. The residue-level chemistry of the protein.
alphafold.ebi.ac.uk
Citation record by ID (typically a PubMed numeric ID).
Raw cross-references to PDB, Pfam, Ensembl, Reactome, KEGG, STRING …
Structured disease records from DISEASE-type comments: name + acronym + UniProt disease ID + OMIM cross-ref + description.
Full UniProt entry (e.g. P04637 for p53). Function, gene, organism, disease, cross-refs.
Domains, binding sites, PTMs, signal peptides — optional type filter.
GO annotations grouped by aspect (F / P / C).
Keyword by ID (e.g. KW-0007 = Acetylation). Definition, synonyms, GO refs, hierarchy.
Maturation features: signal peptide, propeptide, transit peptide, initiator methionine, chain, peptide. Essential for therapeutic-protein engineering and pathogen-secretion analysis.
Proteome by UP ID (UP000005640 = human). Counts, BUSCO score, components.
Post-translational modifications: modified residues (phospho/acetyl/methyl), glycosylation, lipidation (GPI/prenyl/palmitoyl), disulfide bonds, cross-links.
rest.uniprot.org
FASTA. PIR-style provenance comment block above the first record (BLAST+ / biopython compatible).
Subcellular-location term by ID (e.g. SL-0039 = Cell membrane).
Sequence-archive record by UPI (UPI000002ED67).
UniRef cluster by ID (UniRef50P04637, UniRef90P04637, UniRef100P04637).
Natural variants and disease mutations.
Map IDs between databases (GeneName → UniProtKB, PDB → UniProtKB, …).
HGVS-shorthand match (R175H, V600E, R248) against UniProt's natural-variant features.
Re-fetch a previously recorded URL and compare release tag + canonical response SHA-256. Five verdicts (verified, releasedrift, hashdrift, releaseandhashdrift, urlunreachable) each with an advice string.
AlphaFold model id + EBI viewer URL (model id only — for pLDDT call the dedicated tool below).
ChEMBL drug-target id + EBI target-card URL.
eutils.ncbi.nlm.nih.gov
InterPro signatures: id + entry name.
Group orthology cross-references by source DB (KEGG / OMA / OrthoDB / eggNOG / 8 more).
PDB structures: id + method + resolution + chain coverage.
UniProt query language — gene, organism, taxon ID, reviewed flag, free text.
Index search across UniProt citations.
Free-text keyword search.
Filter by organism / type / completeness.
Free-text location search.
UniParc full-text search.
Cluster search with identitytier filter (50 / 90 / 100).
One-call comprehensive characterisation: nine sections — identity / function / chemistry / structure / drug-target / disease / variants / functional annotations / cross-refs.
Search UniProt taxonomy by organism name.