Advertise
MCP.so
Sign In

mcp-pkm-logseq MCP server

@ruliana

Repository

Basic information

Category

Memory & Knowledge

Last updated

License

MIT

Transports

stdio

Author

ruliana

About mcp-pkm-logseq MCP server

A fairly customizable MCP server for Logseq

mcp-pkm-logseq MCP server config

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

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

mcp-pkm-logseq MCP server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

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.

Frequently asked questions

1

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.

2

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.

3

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"]`.

4

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.

5

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

Konshus.AI

Konshus

Your own memory for every AI. Konshus brings in your ChatGPT, Claude, Gemini and Grok chats, notes and journals, and shares one private memory with Claude, ChatGPT, Cursor, Zed and more.

Sensefold

SenseFold Labs

Personal context for every AI: search, read, and write back to your private Markdown library of articles, threads, PDFs, notes, and captured ChatGPT/Claude/Gemini/Grok conversations. Remote server, OAuth 2.1 paste-and-au

agentleFS

agentleFS

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

Oort

Oort

Memory for AI agents that stays correct as facts change. Open source and local first: one memory for Claude Code, Codex, Cursor and your own agents.

1

Tempreon

Tempreon

Person-owned, portable AI memory served over MCP. Your knowledge, preferences, and decisions — captured in one assistant, available in all of them.

Advertise