LogSeq

v1.0.0Knowledge & Memorystable

MCP server to interact with LogSeq via its Local HTTP API - enabling AI assistants like Claude to seamlessly read, write, and manage your LogSeq graph.

knowledge-baseknowledge-managementlogseqmcpmcp-server
Share:
271
Stars
0
Downloads
0
Weekly
0/5

What is LogSeq?

LogSeq is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server to interact with logseq via its local http api - enabling ai assistants like claude to seamlessly read, write, and manage your logseq graph.

MCP server to interact with LogSeq via its Local HTTP API - enabling AI assistants like Claude to seamlessly read, write, and manage your LogSeq graph.

This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • MCP server to interact with LogSeq via its Local HTTP API -

Use Cases

Manage your LogSeq graph through a local HTTP API.
Seamlessly read and write to your knowledge management system.
Integrate LogSeq with Claude and other AI assistants.
ergut

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 20, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx mcp-logseq

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use LogSeq

MCP server for LogSeq connects AI assistants like Claude to your local LogSeq knowledge graph via LogSeq's built-in HTTP API, enabling them to read, create, update, and delete pages without leaving the chat interface. It supports 16 core tools for page management, search, and Datalog queries, plus optional vector search via Ollama and LanceDB for semantic retrieval across your notes. Knowledge workers and developers use it to automate note-taking, extract insights from large knowledge bases, and have AI assistants manage their personal knowledge graphs hands-free.

Prerequisites

  • LogSeq desktop app installed and running with a graph open
  • LogSeq HTTP API enabled in Settings > Features > Enable HTTP APIs server
  • A LogSeq API token generated from the API panel
  • Python package manager uv installed
  • An MCP-compatible client such as Claude Desktop or Claude Code
1

Enable the LogSeq HTTP API

In LogSeq, go to Settings > Features and toggle on 'Enable HTTP APIs server'. Then click the plug icon in the toolbar and select 'Start server'. The server runs on port 12315 by default.

2

Generate a LogSeq API token

In the LogSeq API panel that appeared after starting the server, navigate to Authorization tokens and generate a new token. Copy this token — it is your LOGSEQ_API_TOKEN.

3

Add the MCP server to Claude Code

Register mcp-logseq with Claude Code using the claude mcp add command, passing your token and the LogSeq API URL as environment variables.

claude mcp add mcp-logseq \
  --env LOGSEQ_API_TOKEN=your_token_here \
  --env LOGSEQ_API_URL=http://localhost:12315 \
  -- uv run --with mcp-logseq mcp-logseq
4

Or configure Claude Desktop manually

For Claude Desktop, add the server block to claude_desktop_config.json with your token and the default LogSeq API URL.

{
  "mcpServers": {
    "mcp-logseq": {
      "command": "uv",
      "args": ["run", "--with", "mcp-logseq", "mcp-logseq"],
      "env": {
        "LOGSEQ_API_TOKEN": "your_token_here",
        "LOGSEQ_API_URL": "http://localhost:12315"
      }
    }
  }
}
5

Verify and start querying your knowledge base

Restart your MCP client and confirm the server connects. You can then ask Claude to list your pages, search by keyword, or create new notes. For semantic search, additionally install Ollama and configure the optional vector search tools.

LogSeq Examples

Client configuration

Claude Desktop config for mcp-logseq with LogSeq API token and local server URL.

{
  "mcpServers": {
    "mcp-logseq": {
      "command": "uv",
      "args": ["run", "--with", "mcp-logseq", "mcp-logseq"],
      "env": {
        "LOGSEQ_API_TOKEN": "your_token_here",
        "LOGSEQ_API_URL": "http://localhost:12315",
        "LOGSEQ_EXCLUDE_TAGS": "private,secret"
      }
    }
  }
}

Prompts to try

Sample prompts for managing and querying your LogSeq knowledge graph.

- "List all pages in my LogSeq graph related to machine learning"
- "Create a new page called 'Today's Standup' with bullet points for updates, blockers, and next steps"
- "Analyze my project notes from the past month and create a status summary page"
- "Find all pages that link back to my 'Product Roadmap' page"
- "Search for everything I've written about burnout, even if I didn't use that exact word"

Troubleshooting LogSeq

Connection refused error when trying to reach the LogSeq API

Make sure LogSeq is running, the graph is open, and the HTTP API server has been started from the API panel (click the plug icon and choose 'Start server'). The default port is 12315. Verify with: curl http://localhost:12315/api.

Authentication error — 401 Unauthorized from the LogSeq API

Regenerate your API token from the LogSeq API panel and update the LOGSEQ_API_TOKEN env var in your MCP config. Token values are sensitive — ensure there are no trailing spaces or line breaks when copying.

uv command not found when starting the MCP server

Install uv with: curl -LsSf https://astral.sh/uv/install.sh | sh and ensure it is on the PATH visible to your MCP client. On macOS you may need to add ~/.cargo/bin to the PATH in your shell profile.

Frequently Asked Questions about LogSeq

What is LogSeq?

LogSeq is a Model Context Protocol (MCP) server that mcp server to interact with logseq via its local http api - enabling ai assistants like claude to seamlessly read, write, and manage your logseq graph. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install LogSeq?

Follow the installation instructions on the LogSeq GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with LogSeq?

LogSeq works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is LogSeq free to use?

Yes, LogSeq is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Knowledge & Memory MCP Servers

Explore all knowledge & memory servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "mcp-logseq": { "command": "npx", "args": ["-y", "mcp-logseq"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use LogSeq?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides