Logseq MCP Tools

A Model Context Protocol (MCP) server that provides AI assistants with structured access to your Logseq knowledge graph.

Overview

This project creates an MCP server that allows AI assistants like Claude to interact with your Logseq knowledge base. It provides tools for:

• Retrieving a list of all pages
• Getting content from specific pages
• Generating journal summaries for flexible date ranges
• Extracting linked pages and exploring connections

Installation

Installing via Smithery

To install Logseq Tools for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @joelhooks/logseq-mcp-tools --client claude

1. Clone this repository
2. Install dependencies using npm, yarn, or pnpm:

# Using npm
npm install

# Using yarn
yarn install

# Using pnpm
pnpm install

3. Copy the environment template and configure your Logseq token:

cp .env.template .env
# Edit .env with your Logseq authentication token

Configuration

This project includes a .env.template file that you can copy and rename to .env.

You can find your Logseq auth token by:

1. Opening Logseq
2. Enabling the HTTP API in Settings > Features > Enable HTTP API
3. Setting your authentication token in Settings > Features > HTTP API Authentication Token

Usage

Running the MCP Server

The server can be started using:

# Using the npm script
npm start

# Or directly with tsx
npx tsx index.ts

Connecting with Claude

Claude Desktop

Follow the Claude MCP Quickstart guide:

1. Important: Install Node.js globally via Homebrew (or whatever):

brew install node

2. Install the Claude desktop app
3. Open the Claude menu and select "Settings..."
4. Click on "Developer" in the left sidebar, then click "Edit Config"
5. This will open your claude_desktop_config.json file. Replace its contents with:

{
  "mcpServers": {
    "logseq": {
      "command": "npx",
      "args": [
        "tsx",
        "/path/to/your/index.ts"
      ]
    }
  }
}

IMPORTANT: Replace /path/to/your/index.ts with the exact absolute path to your index.ts file (e.g., /Users/username/Code/logseq-mcp-tools/index.ts)

6. Save the file and restart Claude Desktop

Now you can chat with Claude and ask it to use your Logseq data:

• "Show me my recent journal entries"
• "Summarize my notes from last week"
• "Find all pages related to [topic]"

Claude in Cursor

Follow the Cursor MCP documentation:

1. Open Cursor
2. Add a new MCP service from settings
3. Enter the following command:

npx tsx "/path/to/index.ts"

4. Give your service a name like "Logseq Tools"

Now you can use Claude in Cursor with your Logseq data.

Claude in Anthropic API (generic)

When using the Claude API or CLI tools, you can add the MCP service with:

claude mcp add "logseq" npx tsx "/path/to/index.ts"

Jetbrains Junie Setup

To run this project with JetBrains Junie, follow these steps:

Build the Docker image:

docker build -t logseq-mcp .
# run in project root

Then add the following config to your Junie MCP configuration:

    "logseq": {
      "command": "c:\\Program Files\\Docker\\Docker\\resources\\bin\\docker.exe",
      "args": [
        "run",
        "-i",
        "--rm",
        "--network=host",
        "-e",
        "LOGSEQ_TOKEN=<Your Token>",
        "-e",
        "LOGSEQ_HOST=host.docker.internal",
        "logseq-mcp"
      ]
    }

Available Tools

getAllPages

Retrieves a list of all pages in your Logseq graph.

getPage

Gets the content of a specific page.

Parameters:

• pageName: The name of the page to ret

... View full README on GitHub