What authentication is required to use Release Notes Server?
A GitHub personal access token with repository access must be provided via the `GITHUB_TOKEN` environment variable.
@nickbaumann98
基本信息
An MCP server for generating release notes from GitHub commits
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Release Notes Server is an MCP server that generates beautiful release notes from GitHub repositories. It fetches commits, organizes them by type (features, fixes, etc.), and presents them in a clean, readable Markdown format with emojis and statistics. It is designed for developers and teams who need to produce structured release summaries from GitHub projects.
Install the package via npm install and build it with npm run build. Add the server to your MCP configuration by specifying the node command pointing to the built index.js and providing a GITHUB_TOKEN environment variable for repository access. Invoke the generate_release_notes tool with parameters for owner, repo name, commit range (optional from/to SHA), and format options (type, grouping, statistics).
since parameterA GitHub personal access token with repository access must be provided via the `GITHUB_TOKEN` environment variable.
The release notes are generated in Markdown format, with sections for each commit type (e.g., 🚀 Features, 🐛 Fixes) and optional statistics.
Commits are filtered by a date range or by commit SHA using GitHub’s `since` parameter when possible, with fallback to SHA-based filtering as needed.
It accepts `owner`, `repo`, a `commitRange` object with optional `fromCommit` and `toCommit` strings, and a `format` object specifying output type (`markdown`), grouping method (`type`), and whether to include statistics.
The server handles pagination efficiently and maintains newest-first ordering, but no specific rate limits or runtime constraints are documented in the README.

Local AI agent for your Mac with a built-in MCP server: 18 tools for your notes and PDFs, a temporal memory graph, an on-device LLM and a neural voice. No account, no telemetry. No data centers required.

Persistent memory for AI agents. Hosted MCP server with capsule-scoped key/value storage, tags, TTL expiration, bulk ops, and RBAC.
Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.

MCP connector for Snipara, the Project Brain for AI coding agents

One permissioned folder your team and your AI agents both log into.
评论