Logseq Tools
A Model Context Protocol server that provides AI assistants with structured access to your Logseq knowledge graph, enabling retrieval, searching, analysis, and creation of content within your personal knowledge base.
What is Logseq Tools?
Logseq Tools is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol server that provides ai assistants with structured access to your logseq knowledge graph, enabling retrieval, searching, analysis, and creation of content within your personal k...
A Model Context Protocol server that provides AI assistants with structured access to your Logseq knowledge graph, enabling retrieval, searching, analysis, and creation of content within your personal knowledge base.
This server falls under the Knowledge & Memory category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Model Context Protocol server that provides AI assistants
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx logseq-mcp-toolsConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Logseq Tools
Logseq MCP Tools is an MCP server that gives AI assistants like Claude structured, read-write access to your Logseq personal knowledge graph via Logseq's HTTP API. It exposes tools for listing and retrieving pages, generating journal summaries across flexible date ranges, searching pages, creating new pages, analyzing the graph for knowledge gaps, finding backlinks, and suggesting connections between topics. This makes it possible to ask Claude to summarize last week's journal, find all notes related to a project, or create a new page — all without leaving your conversation.
Prerequisites
- Node.js 18+ installed (Homebrew recommended on macOS: brew install node)
- Logseq desktop app running with HTTP API enabled (Settings > Features > Enable HTTP API)
- A Logseq HTTP API authentication token (Settings > Features > HTTP API Authentication Token)
- Git to clone the repository: https://github.com/joelhooks/logseq-mcp-tools
- An MCP-compatible client such as Claude Desktop or Cursor
Install via Smithery (easiest)
The fastest way to get started is via Smithery, which handles installation and Claude Desktop configuration automatically.
npx -y @smithery/cli install @joelhooks/logseq-mcp-tools --client claudeOr clone and install manually
Alternatively, clone the repo and install dependencies with npm, yarn, or pnpm.
git clone https://github.com/joelhooks/logseq-mcp-tools.git
cd logseq-mcp-tools
npm installConfigure environment variables
Copy the env template and set your Logseq token. The LOGSEQ_TOKEN is required; LOGSEQ_HOST defaults to localhost.
cp .env.template .env
# Edit .env and set:
# LOGSEQ_TOKEN=your_logseq_http_api_token
# LOGSEQ_HOST=localhostEnable Logseq HTTP API
In Logseq, open Settings > Features, enable the HTTP API toggle, and copy your authentication token. Logseq must be running for the MCP server to connect.
Configure Claude Desktop
Edit your claude_desktop_config.json and point the args to the absolute path of index.ts in your cloned repository.
{
"mcpServers": {
"logseq": {
"command": "npx",
"args": [
"tsx",
"/absolute/path/to/logseq-mcp-tools/index.ts"
]
}
}
}Restart Claude Desktop and test
Restart Claude Desktop with Logseq open in the background. Ask Claude to list your recent journal entries to verify the connection is working.
Logseq Tools Examples
Client configuration (Claude Desktop)
Place this in your claude_desktop_config.json. Replace the path with the actual absolute path to your cloned index.ts file.
{
"mcpServers": {
"logseq": {
"command": "npx",
"args": [
"tsx",
"/Users/yourname/logseq-mcp-tools/index.ts"
]
}
}
}Prompts to try
Interact with your Logseq knowledge graph using natural language through Claude.
- "Show me my recent journal entries from the past week"
- "Summarize my notes from last month"
- "Find all pages related to machine learning in my graph"
- "Create a new page called 'Project Alpha' with a summary of our goals"
- "What knowledge gaps exist in my notes on distributed systems?"Troubleshooting Logseq Tools
Connection refused error when the server starts
Make sure Logseq is running and the HTTP API is enabled in Settings > Features. The server connects to localhost by default on the port Logseq's HTTP API uses. If you run Logseq in Docker, set LOGSEQ_HOST=host.docker.internal in your .env file.
Authentication error or 401 response from Logseq
Check that LOGSEQ_TOKEN in your .env file matches the token shown in Logseq Settings > Features > HTTP API Authentication Token exactly. Regenerating the token in Logseq and updating .env fixes most auth issues.
npx tsx fails with 'tsx not found'
Ensure Node.js 18+ is installed globally (brew install node on macOS). Then run npm install in the cloned repository to install tsx as a local dependency. The npx command will pick it up from node_modules.
Frequently Asked Questions about Logseq Tools
What is Logseq Tools?
Logseq Tools is a Model Context Protocol (MCP) server that model context protocol server that provides ai assistants with structured access to your logseq knowledge graph, enabling retrieval, searching, analysis, and creation of content within your personal knowledge base. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Logseq Tools?
Follow the installation instructions on the Logseq Tools GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Logseq Tools?
Logseq Tools works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Logseq Tools free to use?
Yes, Logseq Tools is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.
Logseq Tools Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to Logseq Tools? Here are other popular knowledge & memory servers you can use with Claude, Cursor, and VS Code.
MemPalace
★ 52.6kA local AI memory system that stores all conversations verbatim and organizes them into navigable structures. It provides 19 MCP tools for AI assistants to search and retrieve past decisions, debugging sessions, and architecture debates automatically
Kratos
★ 25.7k🏛️ Memory System for AI Coding Tools - Never explain your codebase again. MCP server with perfect project isolation, 95.8% context accuracy, and the Four Pillars Framework.
Context Mode
★ 15.4kAn MCP server that preserves LLM context by intercepting large data outputs and returning only concise summaries or relevant sections. It enables efficient sandboxed code execution, file processing, and documentation indexing across multiple programm
Memu
★ 13.7kMemory for 24/7 proactive agents like OpenClaw.
MemOS
★ 9.3kMemOS (Memory Operating System) is a memory management operating system designed for AI applications. Its goal is: to enable your AI system to have long-term memory like a human, not only remembering what users have said but also actively invoking, u
Everos
★ 5.4kBuild, evaluate, and integrate long-term memory for self-evolving agents.
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.
Set Up Logseq Tools in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Logseq Tools?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.