Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

logseq-mcp

MCP.Pizza Chef: dailydaniel

logseq-mcp is a Model Context Protocol server that integrates directly with Logseq's knowledge base. It allows large language models to interact with Logseq graphs, create and manage pages and blocks, and organize information programmatically. This server facilitates seamless automation and AI-driven workflows within Logseq, enhancing knowledge management and note-taking capabilities.

Use This MCP server To

Create and edit Logseq pages programmatically via LLMs Insert and update blocks within Logseq graphs automatically Organize and structure Logseq knowledge bases using AI Enable LLMs to query and retrieve Logseq graph data Automate note-taking and knowledge management workflows Integrate Logseq with AI copilots for enhanced productivity

README

Logseq MCP Server

A Model Context Protocol server that provides direct integration with Logseq's knowledge base. This server enables LLMs to interact with Logseq graphs, create pages, manage blocks, and organize information programmatically.

Usage with Claude Desktop

{
  "mcpServers": {
    "logseq": {
      "command": "uvx",
      "args": ["mcp-server-logseq"],
      "env": {
        "LOGSEQ_API_TOKEN": "<YOUR_KEY>",
        "LOGSEQ_API_URL": "http://127.0.0.1:12315"
      }
    }
  }
}

If you have errors, use 0.0.1 version:

{
  "mcpServers": {
    "logseq": {
      "command": "uvx",
      "args": ["mcp-server-logseq==0.0.1"],
      "env": {
        "LOGSEQ_API_TOKEN": "<YOUR_KEY>",
        "LOGSEQ_API_URL": "http://127.0.0.1:12315"
      }
    }
  }
}

Available Tools

Block Operations

  • logseq_insert_block - Create new blocks in Logseq Parameters:

    • parent_block (string): Parent block UUID or page name
    • content (string, required): Block content
    • is_page_block (boolean): Create as page-level block
    • before (boolean): Insert before parent block
    • custom_uuid (string): Custom UUIDv4 for block
  • logseq_edit_block - Enter block editing mode Parameters:

    • src_block (string, required): Block UUID
    • pos (number): Cursor position
  • logseq_exit_editing_mode - Exit editing mode Parameters:

    • select_block (boolean): Keep block selected

Page Operations

  • logseq_create_page - Create new pages Parameters:

    • page_name (string, required): Page name
    • properties (object): Page properties
    • journal (boolean): Create as journal page
    • format (string): Page format (markdown/org)
  • logseq_get_page - Get page details Parameters:

    • src_page (string, required): Page identifier
    • include_children (boolean): Include child blocks
  • logseq_get_all_pages - List all pages Parameters:

    • repo (string): Repository name

Content Retrieval

  • logseq_get_current_page - Get active page/block Parameters: None

  • logseq_get_current_blocks_tree - Current page's block hierarchy Parameters: None

  • logseq_get_editing_block_content - Get content of active block Parameters: None

  • logseq_get_page_blocks_tree - Get page's block structure Parameters:

    • src_page (string, required): Page identifier

Prompts

logseq_insert_block

Create a new block in Logseq Arguments:

  • parent_block: Parent block reference (page name or UUID)
  • content: Block content
  • is_page_block: Set true for page-level blocks

logseq_create_page

Create a new Logseq page Arguments:

  • page_name: Name of the page
  • properties: Page properties as JSON
  • journal: Set true for journal pages

Installation

Using pip

pip install mcp-server-logseq

From source

git clone https://github.com/dailydaniel/logseq-mcp.git
cd logseq-mcp
cp .env.example .env
uv sync

Run the server:

python -m mcp_server_logseq

Configuration

API Key

  1. Generate API token in Logseq: API → Authorization tokens
  2. Set environment variable:
export LOGSEQ_API_TOKEN=your_token_here

Or pass via command line:

python -m mcp_server_logseq --api-key=your_token_here

Graph Configuration

Default URL: http://localhost:12315 To customize:

python -m mcp_server_logseq --url=http://your-logseq-instance:port

Examples

Create meeting notes page

Create new page "Team Meeting 2024-03-15" with properties:
- Tags: #meeting #engineering
- Participants: Alice, Bob, Charlie
- Status: pending

Add task block to existing page

Add task to [[Project Roadmap]]:
- [ ] Finalize API documentation
- Due: 2024-03-20
- Priority: high

Create journal entry with first block

Create journal entry for today with initial content:
- Morning standup completed
- Started work on new authentication system

Debugging

npx @modelcontextprotocol/inspector uv --directory . run mcp-server-logseq

Contributing

We welcome contributions to enhance Logseq integration:

  • Add new API endpoints (page linking, query support)
  • Improve block manipulation capabilities
  • Add template support
  • Enhance error handling

logseq-mcp FAQ

How do I authenticate the logseq-mcp server?
You authenticate using the LOGSEQ_API_TOKEN environment variable with your API key.
Can I run logseq-mcp locally?
Yes, you can run it locally by setting LOGSEQ_API_URL to your local Logseq instance URL.
What operations can I perform with logseq-mcp?
You can create pages, insert and update blocks, and organize Logseq content programmatically.
Is logseq-mcp compatible with multiple LLM providers?
Yes, it works with OpenAI, Anthropic Claude, and Google Gemini models via MCP clients.
How do I handle version issues with logseq-mcp?
Use the specified version 0.0.1 if you encounter errors with the latest release.
What is required to start the logseq-mcp server?
You need the command 'uvx' with the argument 'mcp-server-logseq' and proper environment variables set.
Can logseq-mcp manage tags within Logseq?
Currently, it focuses on block and page operations; tag management may require additional tooling.
How does logseq-mcp improve AI workflows?
It enables real-time, programmatic interaction with Logseq, allowing AI to manage and query knowledge bases efficiently.