Zettelkasten MCP Server

What is Zettelkasten MCP Server?

A Model Context Protocol (MCP) server that implements the Zettelkasten knowledge management methodology, enabling users to create, link, explore, and synthesize atomic notes through Claude and other MCP-compatible clients.

How to use Zettelkasten MCP Server?

Install by cloning the repository, creating a virtual environment with uv venv, and adding the mcp[cli] dependency. Configure a .env file from .env.example. Start the server with python -m zettelkasten_mcp.main (optionally with --notes-dir and --database-path). Connect to Claude Desktop by adding an MCP server entry in its configuration pointing to the Python executable and the module.

Key features of Zettelkasten MCP Server

• Create atomic notes with unique timestamp-based IDs
• Link notes bidirectionally to build a knowledge graph
• Tag notes for categorical organization
• Search notes by content, tags, or links
• Use human‑readable Markdown with YAML frontmatter
• Dual storage: Markdown files (source of truth) + SQLite index
• Supports five note types: fleeting, literature, permanent, structure, hub
• Provides 14 MCP tools (all prefixed with zk_)

Use cases of Zettelkasten MCP Server

• Build a personal knowledge network of linked atomic ideas
• Capture and organize insights from reading (literature notes)
• Discover emergent patterns by traversing semantic links between notes
• Use Claude as an AI assistant to create, explore, and synthesize notes
• Maintain a version‑controlled, backup‑friendly knowledge base

FAQ from Zettelkasten MCP Server

What storage architecture does the server use?

Notes are stored as Markdown files with YAML frontmatter (the source of truth) and indexed in a SQLite database for efficient querying and graph traversal. The database can be rebuilt from the Markdown files at any time.

What note and link types are available?

Notes can be fleeting, literature, permanent, structure, or hub. Links support seven semantic types – reference, extends, refines, contradicts, questions, supports, and related – each with a defined inverse relationship.

What are the runtime dependencies?

Python 3, uv, and the mcp[cli] package. The server is run as a Python module (zettelkasten_mcp.main) and connects to MCP‑compatible clients.

Where does the data live?

Note content is stored in a user‑configured data/notes directory as Markdown files. The SQLite index resides in data/db/. Both paths are set via environment variables or command‑line arguments.

Is the server safe for production use?

No. The README states the software is experimental and provided as‑is without warranty. It may contain bugs that could lead to data loss or corruption. Regular backups are recommended.