What file format does 📚 MCP Notes use?
All notes are stored as plain text Markdown files, ensuring future‑proof portability, version control compatibility, and easy editing with any text editor.
@markacianfrani
基本信息
an MCP server for makin' notes
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。
📚 MCP Notes is a personal knowledge management system built on the Model Context Protocol (MCP) that transforms daily notes into organized, searchable knowledge. It helps users capture thoughts quickly, organize them automatically, and retrieve them easily.
Clone the repository, run npm i and npm run build, then add a configuration entry to your Claude Desktop JSON to point to the compiled server and a notes directory. Once configured, invoke tools like /log, /rollup, write_note, sticky, or evaluateInsight through any MCP‑compatible client to capture, categorize, and retrieve notes.
All notes are stored as plain text Markdown files, ensuring future‑proof portability, version control compatibility, and easy editing with any text editor.
Notes start as daily logs (one Markdown file per day). Rollups automatically condense daily logs into higher‑level summaries, and all notes are classified into four categories: Accomplishment, Insight, TODO, and Knowledge.
Core tools include `/log` (create/update daily log), `/rollup` (synthesize daily notes), `write_note`, `sticky` (evaluate thought stickiness), and `evaluateInsight`. File system tools include `search_files`, `read_note`, `read_multiple_notes`, `list_directory`, and `create_directory`.
It is tool‑agnostic and works with any MCP‑compatible client, such as Claude Desktop, Copilot, or Cursor. A manual setup with the Claude Desktop configuration is provided as an example.
Node.js and npm are required to build the server from source. The notes directory path is provided as a command‑line argument when starting the server.
Local MCP server and CLI that keeps a Git-versioned, model-written index of a codebase and its database schema, so coding agents start each task with the whole system in view.

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

Sooveryn gives Claude Code a team of AI personas that remembers your project. Soov, the partner and team lead, keeps your decisions and how you work in a lasting memory, and finds them again by words and by meaning, from
Project context your AI can query through MCP — with source evidence.
Shared, serverless, conflict-free memory for AI agents: a multi-machine drop-in for the MCP memory knowledge graph.
评论