MCP.so
Sign In

mcp-pkm-logseq MCP server

@ruliana

About mcp-pkm-logseq MCP server

A fairly customizable MCP server for Logseq

Basic information

Category

Memory & Knowledge

License

MIT

Runtime

python

Transports

stdio

Publisher

ruliana

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-pkm-logseq": {
      "command": "uv",
      "args": [
        "sync"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is mcp-pkm-logseq?

mcp-pkm-logseq is an MCP server that enables AI assistants to interact with your Logseq Personal Knowledge Management system. It provides tools to retrieve notes and todos from your Logseq graph, guided by a custom instructions page you create. It is intended for users who want LLM-powered access to their Logseq knowledge base.

How to use mcp-pkm-logseq?

Install via uvx mcp-pkm-logseq and configure the environment variables LOGSEQ_API_KEY (default "this-is-my-logseq-mcp-token") and LOGSEQ_URL (default "http://localhost:12315"). Enable Logseq’s built-in HTTP API server in Settings → Advanced → Developer mode, set your API token, then configure your MCP client (e.g., Claude Desktop, Claude Code, Cursor) with the server command and environment variables. A page named “MCP PKM Logseq” should be created in your graph to serve as an AI guide.

Key features of mcp-pkm-logseq?

  • Provides a guide resource (logseq://guide) for assistant instructions.
  • Retrieve personal notes by topic and date range.
  • Retrieve todo items filtered by done status and date range.
  • Configurable API token and Logseq server URL.
  • Integrates with Logseq’s HTTP API (port 12315 default).

Use cases of mcp-pkm-logseq?

  • An AI assistant retrieves notes tagged with specific topics from your Logseq graph.
  • A chatbot fetches your current or past todos to help with task management.
  • A personal knowledge assistant uses the guide page to learn your tagging conventions before searching.

FAQ from mcp-pkm-logseq

What environment variables does mcp-pkm-logseq require?

LOGSEQ_API_KEY (default: "this-is-my-logseq-mcp-token") for authentication and LOGSEQ_URL (default: "http://localhost:12315") for the Logseq HTTP API endpoint.

How do I enable the Logseq HTTP API?

Open Logseq, go to Settings → Advanced, enable “Developer mode” and “HTTP API Server”, then set your API token to match the LOGSEQ_API_KEY value.

Where do I configure mcp-pkm-logseq for Claude Desktop?

On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json; on Windows: %APPDATA%/Claude/claude_desktop_config.json. Add the server under mcpServers with "command": "uvx" and "args": ["mcp-pkm-logseq"].

What is the “MCP PKM Logseq” page for?

It is a guide page you create in your Logseq graph containing your tagging system, workflows, naming conventions, and search preferences. The server exposes it as a resource so the AI assistant can understand how to interact with your knowledge base.

How can I debug the server during development?

Use the MCP Inspector by running npx @modelcontextprotocol/inspector uv --directory <path> run mcp-pkm-logseq. This provides a browser-based debugging interface.

Comments

More Memory & Knowledge MCP servers