UniProt
A UniProt MCP server built by Jose Duarte that provides read-only access to the UniProtKB protein database through five core tools: fetch_entry for complete protein entries, get_sequence for protein sequences, search_uniprot for filtered searches, map_ids for converting between 200+ database identifier types, and fetch_entry_flatfile for historical entry versions. The implementation features retry logic with exponential backoff, progress reporting for long-running ID mapping jobs, both stdio and HTTP transports with CORS support, and structured Pydantic models for type-safe responses. Useful for bioinformatics workflows, protein research, database integration projects, and AI agents that need reliable access to curated protein data from one of the world's primary protein sequence databases.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/josefdc/uniprot-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve UniProt from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.