git-notes-memory
🧠Store and search your notes effectively with Git-native memory storage, enhancing productivity for Claude Code users.
claude mcp add --transport stdio fnbdesign-git-notes-memory node path/to/server.js \ --env GENERIC_ENV_PLACEHOLDER="Set environment variables as needed by the server (e.g., API keys, storage paths)."
How to use
git-notes-memory provides a lightweight way to store and search coding insights using a familiar Git notes format, with a built-in vector search to quickly surface relevant decisions and learnings. The server-side tooling is designed to index notes stored in Git notes and enable semantic search across your repository history and notes corpus. Once running, you can add notes with a clear title and content, and then use the search interface to retrieve contextually relevant notes based on keywords, concepts, or related code snippets. The workflow emphasizes using Git for versioning your notes, ensuring you can track changes over time just like your code.
To use the tools, start the MCP server and connect to its search interface or API endpoints. Create new notes by providing titles and content, then save them to the notes store. Use the built-in search to locate notes by keywords, phrases, or related topics. You can edit or delete notes as your understanding evolves. This setup is particularly useful for capturing decisions, design considerations, and coding insights while progressing through a project, and then retrieving them later through semantic or keyword-based queries.
How to install
Prerequisites:
- Node.js (version compatible with the server script) or a compatible runtime environment where the server can be executed
- Access to the file system to store notes and index data
- Basic shell or terminal for running commands
Steps:
- Clone/download the repository containing git-notes-memory to your local machine.
- Ensure you have Node.js installed. You can check with:
- node -v
- Install dependencies if a package.json exists (navigate to the project directory and run):
- npm install
- Prepare to run the server. If a server entry point is provided, edit the path in the MCP config (see mcp_config) to point to your server script, e.g., path/to/server.js.
- Start the MCP server using your preferred method (as defined by your MCP orchestration), for example:
- npm start
- Verify the server is running by visiting the API endpoint or UI URL defined by the project documentation. Ensure you can create and search notes.
Notes:
- If the project provides a packaged binary or installer, follow the platform-specific instructions and then point the MCP server at the executable or wrapper script.
- If no server script is provided, you may need to adapt the repository to expose a small HTTP API for note creation and search.
Additional notes
Tips and caveats:
- Ensure you have sufficient disk space for note storage and index data.
- When using Git notes, maintain consistent formatting for easy parsing and search indexing.
- If you encounter issues with the search accuracy, consider refining keywords or adding semantic tags to notes.
- Document any environment variables required by the server (e.g., storage paths, API endpoints) in your deployment environment.
- Back up your notes repository regularly, especially if you are storing large numbers of notes or large note content.
Related MCP Servers
grepai
Semantic Search & Call Graphs for AI Agents (100% Local)
claude-code-open
Open source AI coding platform with Web IDE, multi-agent system, 37+ tools, MCP protocol. MIT licensed.
mcp-interactive-terminal
MCP server that gives AI agents (Claude Code, Cursor, Windsurf) real interactive terminal sessions — REPLs, SSH, databases, Docker, and any interactive CLI with clean output and smart completion detection
cadre-ai
Your AI agent squad for Claude Code. 17 specialized agents, persistent memory, desktop automation, and a common sense engine.
markupr
Give your AI coding agent eyes and ears. Screen + voice capture → structured Markdown. MCP server, CLI, and macOS app.
mini_claude
Give Claude Code persistent memory across sessions. Track habits, log mistakes, prevent death spirals. Runs locally with Ollama.