Logseq MCP Tools MCP Server

MCP Server for interacting with LogSeq graph

Local serverstdioPython

What is the Logseq MCP Tools MCP Server?

MCP Server for interacting with LogSeq graph

What the server does

This project provides a set of Model Context Protocol (MCP) tools that enable AI agents to interact with your local Logseq instance.

More MCP options

Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.

Maintainer setup documentation.

Recorded tools

Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.

ToolWhat it does
logseq.get_all_pagesGet a list of all pages in the Logseq graph
logseq.get_pageGet a specific page by name
logseq.create_pageCreate a new page
logseq.delete_pageDelete a page and all its blocks
logseq.get_page_blocksGet all blocks from a specific page
logseq.get_blockGet a specific block by ID
logseq.create_blockCreate a new block on a page
logseq.insert_blockInsert a block as a child of another block
logseq.update_blockUpdate an existing block
logseq.move_blockMove a block to a different location
logseq.remove_blockRemove a block and all its children
logseq.search_blocksSearch for blocks matching a query

How to install the Logseq MCP Tools MCP Server

{
  "mcpServers": {
    "logseq": {
      "command": "/opt/homebrew/bin/uvx",
      "args": [
        "logseq-mcp"
      ],
      "env": {
        "LOGSEQ_API_URL": "http://localhost:12315",
        "LOGSEQ_TOKEN": "YOUR_LOGSEQ_TOKEN"
      }
    }
  }
}

From the project documentation. Replace placeholders and example paths before connecting.

Configuration

VariableDescriptionRequired
LOGSEQ_API_URLDeclared in the maintainer’s client configuration.Check documentation
LOGSEQ_TOKENDeclared in the maintainer’s client configuration.Check documentation

Example prompts to try

  • “Use Logseq MCP Tools to Pages.”
  • “Use Logseq MCP Tools to Blocks.”

Frequently asked questions

Python 3.11+ and a local Logseq instance with Developer mode enabled, Developer Plugin turned on, and an API token set in Advanced settings.