smaniches/uniprot-mcp
by Various
Auditable UniProt MCP server with per-response SHA-256 provenance, release pinning, verification, and offline replay.
MCP
smaniches/uniprot-mcp
Added 3 Sept 2026
Overview
A Model Context Protocol (MCP) server for UniProt data that adds per-response SHA-256 provenance, release pinning, verification, and offline replay. Written in Python, it provides an auditable interface for retrieving protein data with reproducible results.
Best for
Best for
Developers needing auditable, reproducible UniProt data access in MCP workflows
Use cases
- Integrating UniProt data into MCP-based agent workflows
- Auditing the provenance of protein data responses
- Replaying responses from pinned UniProt releases for reproducibility
How to use
Install
uvx uniprot-mcp-server Tools exposed
uniprot_get_entryuniprot_searchuniprot_get_sequenceuniprot_get_featuresuniprot_get_variantsuniprot_get_go_termsuniprot_get_cross_refsuniprot_id_mappinguniprot_batch_entriesuniprot_taxonomy_searchuniprot_get_keyworduniprot_search_keywordsuniprot_get_subcellular_locationuniprot_search_subcellular_locationsuniprot_get_unirefuniprot_search_unirefuniprot_get_uniparcuniprot_search_uniparcuniprot_get_proteomeuniprot_search_proteomes
Tested with
Claude Desktop, Claude Code
Notes
A Model Context Protocol (MCP) server for UniProt data that adds per-response SHA-256 provenance, release pinning, verification, and offline replay. Written in Python, it provides an auditable interface for retrieving protein data with reproducible results.
3 stars on GitHub. Last updated 2026-09-03. Licensed Apache-2.0.
Use cases
- Integrating UniProt data into MCP-based agent workflows
- Auditing the provenance of protein data responses
- Replaying responses from pinned UniProt releases for reproducibility
Pros
- Per-response SHA-256 provenance enables audit trails
- Release pinning and offline replay support reproducible queries
- Simple Python implementation for easy extension
Cons
- Low community adoption (3 stars) suggests limited validation
- Python-only limits use in non-Python environments
- Offline replay requires pre-cached data, which is not documented here
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Per-response SHA-256 provenance enables audit trails
- Release pinning and offline replay support reproducible queries
- Simple Python implementation for easy extension
Cons
- Low community adoption (3 stars) suggests limited validation
- Python-only limits use in non-Python environments
- Offline replay requires pre-cached data, which is not documented here
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.
