ergut/mcp-logseq

What it solves

This project provides a Model Context Protocol (MCP) server that connects AI assistants like Claude to a LogSeq knowledge base. It eliminates the need to manually export or copy notes, allowing an AI to read, create, and manage pages and blocks directly within your LogSeq graph.

How it works

The server acts as a bridge between an MCP-compatible client and the LogSeq HTTP API. It provides a suite of 17 core tools for page and block manipulation, and 3 optional tools for semantic search. It includes a smart markdown parser that converts AI-generated markdown into LogSeq's native block structure, ensuring that headings, nested lists, and properties are preserved.

Who it’s for

Users of LogSeq who want to automate their knowledge management, perform complex analysis across their notes, or use an AI assistant to organize and document their research and meeting notes.

Highlights

• Full Graph Management: Ability to list, read, create, update, and delete pages and blocks.
• Semantic Vector Search: Optional support for finding notes by meaning using local (Ollama) or hosted (OpenAI) embeddings via LanceDB.
• Privacy Controls: Granular access control using excluded tags and namespace allow/deny lists to hide sensitive content from the AI.
• Smart Markdown Parsing: Automatically converts markdown input into structured LogSeq blocks, including support for YAML frontmatter and checkboxes.
• DB-mode Support: Opt-in support for reading and writing class properties on Logseq DB-mode graphs.
• Enterprise-ready Deployment: Supports stdio, HTTP transport with bearer authentication, and TLS for remote clients.