LogSeq
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.
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
Maintainer
Works with
Installation
Manual Installation
npx mcp-logseqConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
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
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.
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.
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-logseqOr 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"
}
}
}
}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.
LogSeq Alternatives — Similar Knowledge & Memory Servers
Looking for alternatives to LogSeq? 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 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?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.