UniProt Protein Research

Live

Match the gene and organism. Inspect the exact protein record.

Find UniProtKB protein-record candidates by literal gene and exact organism, then inspect canonical accession identity, source curation, protein-existence evidence and representative-length metadata. Keep source release, versions and CC BY attribution visible.

Connect this tool ↗Tool reference

Connect / 2 tools

Server URL

streamable http

https://toolcargo.com/mcp/uniprot

Claude Code

terminal

claude mcp add --transport http --scope user toolcargo-uniprot https://toolcargo.com/mcp/uniprot \
  --header "Authorization: Bearer YOUR_API_KEY"

Create a key in your dashboard. Other clients: setup guides.

What it helps you do

Exact gene and organism discovery
Canonical protein record identity
Source curation, evidence and length context

Built for: Research agents identifying protein records without confusing species, isoforms or evidence classes.

Example requests

Identify a human insulin source record

“Search literal gene INS in exact organism taxonomy ID 9606 using reviewed UniProt records. Inspect the exact returned accession, preserve its source names, protein-existence evidence and canonical length, and explain why precursor length is not a mature-chain measurement. Cite UniProt Consortium, source release and CC BY 4.0.”

An exact source protein record with organism, curation, evidence and length context.

Explore useful agent workflows ↗

Tools

Tool	What it does	Access
`uniprot_gene_search` Find protein records by gene and organism	Search a literal gene symbol and exact organism taxonomy ID in public UniProtKB metadata. Reviewed, unreviewed or any status; default reviewed. Up to ten candidates per explicit filter/release-bound cursor page. Preserve source gene spelling, curation and existence-evidence class; no sequence residues or narratives. One shared-plan call.	Read-only
`uniprot_protein_details` Inspect an exact canonical protein accession	Inspect one exact canonical UniProtKB primary accession: bounded names, genes, exact organism, reviewed status, existence evidence, canonical length, precursor flag, entry/sequence versions and source release. Inactive/redirect/not-found/gone remain source states without biological-absence inference or alias substitution. No sequence residues or medical advice. One shared-plan call.	Read-only

Requirements

• Activate Site Audit free and use ToolCargo OAuth or a scoped API key. UniProt public APIs require no provider account, key or fee.

Limitations

• Literal gene symbols and exact organism_id filters only; no descendant-taxonomy searches, query language, sequence similarity, arbitrary fields or organism-name guessing. Candidates do not imply one gene equals one protein.
• Default reviewed means UniProtKB Swiss-Prot curation; unreviewed is TrEMBL computer annotation. Protein-existence classes describe source supporting evidence, not general confidence, sequence correctness or clinical suitability.
• Canonical accession lookup rejects isoform suffixes and silent aliases. Source inactive/deleted, redirect, not-found or gone states do not prove a protein cannot exist. Redirect/replacement pointers are never followed automatically.
• At most ten search records per explicit filter/release-bound cursor page, page cap 1000. Source cursor positions, counts and entries are mutable; changed release requires a new explicit search. No pinned snapshot or automatic harvesting.
• Protein names are capped at twenty, genes at twenty, contained chains at ten, name lists at ten and per-name evidence pointers at five, with counts/truncation. Canonical length can describe a precursor or representative record, not all isoforms or a mature chain.
• Independent exact provider lease; one bounded GET per operation, at least 1100ms completion spacing, retained source cooldowns, 35-second operation budget, 15-second response timeout and 256 KiB cap. No caches, stale fallback, retries, redirects, sequence residues, files, function/disease narratives or medical recommendations.
• Source: UniProt Consortium. Copyrightable source data are CC BY 4.0; credit, license link and ToolCargo modifications are disclosed. Patent/other-rights exceptions remain; source access is not blanket clearance or UniProt endorsement.

Supported clients

“Tested” means we connected that client to this endpoint and ran a tool call ourselves. Recorded client-specific tests currently cover Site Audit. Other connectors use the documented setup until tested in that client.

Claude Code	API key header	Documented, not yet tested	This endpoint has not yet been tested in this client. See the setup guide.
Claude (claude.ai)	OAuth sign-in	Documented, not yet tested	This endpoint has not yet been tested in this client. See the setup guide.
Cursor	API key header	Documented, not yet tested	This endpoint has not yet been tested in this client. See the setup guide.
VS Code (Copilot agent mode)	API key header	Documented, not yet tested	This endpoint has not yet been tested in this client. See the setup guide.
ChatGPT (developer mode)	OAuth sign-in	Documented, not yet tested	This endpoint has not yet been tested in this client. See the setup guide.
MCP Inspector	API key header	Documented, not yet tested	This endpoint has not yet been tested in this client. See the setup guide.

Practical workflows

Research UniProt protein records by gene and species with AI and MCP

Pricing

Included with Site Audit. Each successful search page or exact record lookup uses one shared-plan call. UniProt source data are freely accessible; ToolCargo quotas concern hosting and workflow access.

Free

Try hosted tools with a shared monthly allowance.

50 shared calls/month

Pro

$12/mo

Proposed larger shared allowance; see checkout status on the pricing page.

2,000 shared calls/month

Proposed test price. See the pricing page for checkout status.

Full pricing and billing details