MCP server for LogSeq
MCP server to interact with LogSeq via its API. Enables Claude to read, create, and manage LogSeq pages through a comprehensive set of tools.
โจ What You Can Do
Transform your LogSeq knowledge base into an AI-powered workspace! This MCP server enables Claude to seamlessly interact with your LogSeq graphs.
๐ฏ Real-World Examples
๐ Intelligent Knowledge Management
"Analyze all my project notes from the past month and create a status summary"
"Find pages mentioning 'machine learning' and create a study roadmap"
"Search for incomplete tasks across all my pages"
๐ Automated Content Creation
"Create a new page called 'Today's Standup' with my meeting notes"
"Add today's progress update to my existing project timeline page"
"Create a weekly review page from my recent notes"
๐ Smart Research & Analysis
"Compare my notes on React vs Vue and highlight key differences"
"Find all references to 'customer feedback' and summarize themes"
"Create a knowledge map connecting related topics across pages"
๐ค Meeting & Documentation Workflow
"Read my meeting notes and create individual task pages for each action item"
"Get my journal entries from this week and create a summary page"
"Search for 'Q4 planning' and organize all related content into a new overview page"
๐ก Key Benefits
- Zero Context Switching: Claude works directly with your LogSeq data
- Preserve Your Workflow: No need to export or copy content manually
- Intelligent Organization: AI-powered page creation, linking, and search
- Enhanced Productivity: Automate repetitive knowledge work
๐ Quick Start
Step 1: Enable LogSeq API
- Settings โ Features โ Check "Enable HTTP APIs server"
- Click the API button (๐) in LogSeq โ "Start server"
- Generate API token: API panel โ "Authorization tokens" โ Create new
Step 2: Add to Claude (No Installation Required!)
Claude Code
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
Claude Desktop
Add to your config file (Settings โ Developer โ Edit Config
):
{
"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"
}
}
}
}
Step 3: Start Using!
"Please help me organize my LogSeq notes. Show me what pages I have."
๐ ๏ธ Available Tools
The server provides 6 comprehensive tools:
Tool | Purpose | Example Use |
---|---|---|
list_pages |
Browse your graph | "Show me all my pages" |
get_page_content |
Read page content | "Get my project notes" |
create_page |
Add new pages | "Create a meeting notes page" |
update_page |
Modify existing pages | "Update my task list" |
delete_page |
Remove pages | "Delete the old draft page" |
search |
Find content across graph | "Search for 'productivity tips'" |
โ๏ธ Prerequisites
LogSeq Setup
- LogSeq installed and running
- HTTP APIs server enabled (Settings โ Features)
- API server started (๐ button โ "Start server")
- API token generated (API panel โ Authorization tokens)
System Requirements
- uv Python package manager
- MCP-compatible client (Claude Code, Claude Desktop, etc.)
๐ง Configuration
Environment Variables
LOGSEQ_API_TOKEN
(required): Your LogSeq API tokenLOGSEQ_API_URL
(optional): Server URL (default:http://localhost:12315
)
Alternative Setup Methods
Using .env file
# .env
LOGSEQ_API_TOKEN=your_token_here
LOGSEQ_API_URL=http://localhost:12315
System environment variables
export LOGSEQ_API_TOKEN=your_token_here
export LOGSEQ_API_URL=http://localhost:12315
๐ Verification & Testing
Test LogSeq Connection
uv run --with mcp-logseq python -c "
from mcp_logseq.logseq import LogSeq
api = LogSeq(api_key='your_token')
print(f'Connected! Found {len(api.list_pages())} pages')
"
Verify MCP Registration
claude mcp list # Should show mcp-logseq
Debug with MCP Inspector
npx @modelcontextprotocol/inspector uv run --with mcp-logseq mcp-logseq
๐ Troubleshooting
Common Issues
"LOGSEQ_API_TOKEN environment variable required"
- โ Enable HTTP APIs in Settings โ Features
- โ Click ๐ button โ "Start server" in LogSeq
- โ Generate token in API panel โ Authorization tokens
- โ Verify token in your configuration
"spawn uv ENOENT" (Claude Desktop)
Claude Desktop can't find uv
. Use the full path:
which uv # Find your uv location
Update config with full path:
{
"mcpServers": {
"mcp-logseq": {
"command": "/Users/username/.local/bin/uv",
"args": ["run", "--with", "mcp-logseq", "mcp-logseq"],
"env": { "LOGSEQ_API_TOKEN": "your_token_here" }
}
}
}
Common uv locations:
- Curl install:
~/.local/bin/uv
- Homebrew:
/opt/homebrew/bin/uv
- Pip install: Check with
which uv
Connection Issues
- โ Confirm LogSeq is running
- โ Verify API server is started (not just enabled)
- โ Check port 12315 is accessible
- โ Test with verification command above
๐ฉโ๐ป Development
For local development, testing, and contributing, see DEVELOPMENT.md.
Ready to supercharge your LogSeq workflow with AI?
โญ Star this repo if you find it helpful!