MCP Logseq Server

🚀 MCP Server for LogSeq

An MCP server for interacting with LogSeq via its API.

🚀 Quick Start

This MCP server is designed to interact with LogSeq through its API, offering a range of tools to manage and manipulate LogSeq data.

✨ Features

Tools

The server implements multiple tools to interact with LogSeq:

• list_graphs: List all available graphs.
• list_pages: List all pages in the current graph.
• get_page_content: Return the content of a single page.
• search: Search for content across all pages.
• create_page: Create a new page.
• update_page: Update the content of an existing page.
• delete_page: Delete a page.

Example Prompts

It's advisable to first instruct Claude to use LogSeq, and then it will always invoke the tools.

Example prompts:

• Retrieve and summarize the content of my latest meeting notes.
• Search for all pages mentioning Project X and explain the context.
• Create a new page for today's meeting notes.
• Update the project's status page to show the latest updates.

📦 Installation

LogSeq API Configuration

You can configure the environment variables and LogSeq API settings in two ways:

1. Add to the server configuration (recommended)

{
  "mcp-logseq": {
    "command": "uvx",
    "args": [
      "mcp-logseq"
    ],
    "env": {
      "LOGSEQ_API_TOKEN": "<your_api_token_here>",
      "LOGSEQ_API_URL": "http://localhost:12315"
    }
  }
}

2. Create a .env file in the working directory containing the required variables:

LOGSEQ_API_TOKEN=your_token_here
LOGSEQ_API_URL=http://localhost:12315

💻 Usage Examples

Basic Usage

Here are some examples of how to use the tools provided by the server:

• To list all available graphs:

# This is a pseudo - code example for illustration
# Assume there is a function to call the list_graphs tool
result = call_tool('list_graphs')
print(result)

Advanced Usage

For more complex operations, you can combine multiple tools. For example, to search for pages and then get the content of a specific page:

# Pseudo - code example
search_result = call_tool('search', query='Project X')
page_id = extract_page_id_from_search_result(search_result)
page_content = call_tool('get_page_content', page_id=page_id)
print(page_content)

📚 Documentation

Configuration

LogSeq API Configuration

You can configure the environment variables and LogSeq API settings in two ways:

1. Add to the server configuration (recommended)

{
  "mcp-logseq": {
    "command": "uvx",
    "args": [
      "mcp-logseq"
    ],
    "env": {
      "LOGSEQ_API_TOKEN": "<your_api_token_here>",
      "LOGSEQ_API_URL": "http://localhost:12315"
    }
  }
}

2. Create a .env file in the working directory containing the required variables:

LOGSEQ_API_TOKEN=your_token_here
LOGSEQ_API_URL=http://localhost:12315

Development

Building

To prepare the distribution package:

1. Synchronize dependencies and update the lock file:

uv sync

Debugging

Since the MCP server runs via stdio, debugging can be challenging. For the best debugging experience, we recommend using MCP Inspector.

You can start the MCP Inspector as follows:

npx @modelcontextprotocol/inspector uv --directory /path/to/mcp-logseq run mcp-logseq