69 lines (56 loc) · 2.27 KB

Changelog

All notable changes to this project will be documented in this file.

The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.

Unreleased

Added

Initial documentation improvements

0.1.0 - 2025-10-27

Added

Initial public release
MCP server with stdio and HTTP transports
Five core tools for UniProt data access:
- fetch_entry: Retrieve complete protein entries
- get_sequence: Fetch protein sequences
- search_uniprot: Full-text search with advanced filters
- map_ids: Convert between 200+ database identifier types
- fetch_entry_flatfile: Access historical entry versions
Two MCP resources:
- uniprot://uniprotkb/{accession}: Raw entry JSON
- uniprot://help/search: Search documentation
One MCP prompt:
- "Summarize Protein": Generate structured protein summaries
Retry logic with exponential backoff for API resilience
Progress reporting for long-running ID mapping jobs
CORS support for browser-based clients
Prometheus metrics endpoint
Comprehensive test suite with 77% coverage
Type-safe Pydantic models for all responses
Published to PyPI as uniprot-mcp
Published to MCP Registry as io.github.josefdc/uniprot-mcp

Infrastructure

CI/CD with GitHub Actions (lint, type-check, test)
Automated PyPI publishing on version tags
Automated MCP Registry updates
Development tooling with uv, ruff, mypy
VCR-based integration tests

Documentation

Comprehensive README with quickstart and examples
Contributing guidelines
Code of Conduct (Contributor Covenant 2.1)
Security policy
Developer documentation
Registry publishing guide

Release Process

To create a new release:

Update version in pyproject.toml and server.json
Update this CHANGELOG with release notes
Commit changes: git commit -m "chore: bump version to X.Y.Z"
Create and push tag: git tag vX.Y.Z && git push origin vX.Y.Z
GitHub Actions will automatically:
- Build and publish to PyPI
- Update MCP Registry
- Create GitHub Release

Version History