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-server-for-logseqConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use LogSeq
The MCP server for LogSeq connects AI assistants like Claude to your LogSeq knowledge graph via LogSeq's Local HTTP API, enabling seamless reading, writing, and management of pages, blocks, and metadata without leaving your AI client. It exposes 16 core tools for content management, navigation, search, DSL queries, and backlink traversal, plus an optional set of 3 vector search tools using local Ollama embeddings and LanceDB for semantic memory retrieval. Knowledge workers use it to let AI assistants actively maintain and query their second brain rather than just viewing exported notes.
Prerequisites
- LogSeq installed and running on your machine with the Local HTTP API plugin enabled
- A LogSeq API token generated from the Local HTTP API plugin settings (default port 12315)
- Python 3.10+ and uv package manager installed
- An MCP-compatible client such as Claude Desktop or Claude Code
- Ollama installed locally (optional, only needed for semantic vector search tools)
Enable LogSeq's Local HTTP API plugin
In LogSeq, go to Settings → Plugins and enable the Local HTTP API plugin. Note the API token it generates and confirm it is listening on port 12315.
Install the MCP server via Claude Code
The easiest install method for Claude Code users is the claude mcp add command which installs the package and registers it in one step.
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 add manually to Claude Desktop config
For Claude Desktop, open Settings → Developer → Edit Config and add the server entry with your LogSeq credentials.
{
"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"
}
}
}
}Configure optional settings
Set additional environment variables to customize behavior: hide specific tags from AI, enable DB-mode property support, or point to a JSON config file.
# Optional env vars:
# LOGSEQ_DB_MODE=true # Enable DB-mode graph property support
# LOGSEQ_EXCLUDE_TAGS=private,personal # Comma-separated tags to hide from AI
# LOGSEQ_CONFIG_FILE=/path/to/config.jsonRestart your MCP client and verify
Restart Claude Desktop or your MCP client. The LogSeq tools should appear. Ask Claude to list your pages to confirm the connection is working.
LogSeq Examples
Client configuration
Complete claude_desktop_config.json entry for the LogSeq MCP server with API token authentication.
{
"mcpServers": {
"mcp-logseq": {
"command": "uv",
"args": ["run", "--with", "mcp-logseq", "mcp-logseq"],
"env": {
"LOGSEQ_API_TOKEN": "your_logseq_api_token",
"LOGSEQ_API_URL": "http://localhost:12315",
"LOGSEQ_DB_MODE": "false",
"LOGSEQ_EXCLUDE_TAGS": "private"
}
}
}
}Prompts to try
Example prompts to work with your LogSeq knowledge graph through Claude.
- "Show me all my LogSeq pages"
- "Create a new page called 'Meeting Notes 2026-06-13' with bullet points for agenda, attendees, and action items"
- "Search my graph for notes about burnout and summarize the key themes"
- "Find all pages in the Projects namespace and list their most recent updates"
- "Run a DSL query to find all TODO items across my graph"
- "What pages link back to my 'Productivity Systems' page?"Troubleshooting LogSeq
Connection refused or 'API not reachable' error
Confirm LogSeq is running and the Local HTTP API plugin is enabled and started. The default port is 12315—check the plugin settings to confirm it matches LOGSEQ_API_URL. Some macOS systems require the full URL http://127.0.0.1:12315 rather than localhost.
401 Unauthorized when connecting
The LOGSEQ_API_TOKEN must match the token shown in LogSeq's Local HTTP API plugin settings exactly. If you regenerated the token in LogSeq, update the env value in your MCP config and restart the client.
Semantic search tools not available or returning no results
Semantic vector search requires Ollama running locally with an embedding model pulled (e.g. `ollama pull nomic-embed-text`). Ensure Ollama is running and the embedding endpoint is reachable before expecting the vector search tools to appear.
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 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.