MCP server for LogSeq

@ergut

リポジトリ

基本情報

カテゴリ

メモリとナレッジ

トランスポート

stdio

作者

ergut

MCP server for LogSeq について

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-logseq#logseq #ai-assistant

MCP server for LogSeq の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "mcp-logseq-server": {
      "command": "uv",
      "args": [
        "sync"
      ]
    }
  }
}

MCP server for LogSeq のツール

Lists all available graphs

Lists all pages in the current graph

Return the content of a single page

Search for content across all pages

Create a new page

Update content of an existing page

Delete a page

概要

What is MCP server for LogSeq?

MCP server for LogSeq is an MCP server that enables interaction with LogSeq through its API. It provides a set of tools for reading and writing data, designed for LogSeq users who want to manage their knowledge graph with an AI assistant such as Claude.

How to use MCP server for LogSeq?

Configure the server by providing a LOGSEQ_API_TOKEN and the LOGSEQ_API_URL (default http://localhost:12315) either in the MCP server config or via a .env file. Then run uvx mcp-logseq. After adding it to the MCP client, instruct the assistant to use LogSeq; it will call the available tools automatically.

Key features of MCP server for LogSeq

Lists all available graphs (list_graphs)
Lists all pages in the current graph (list_pages)
Retrieves content of a single page (get_page_content)
Searches content across all pages (search)
Creates a new page (create_page)
Updates an existing page (update_page)
Deletes a page (delete_page)

Use cases of MCP server for LogSeq

Fetch latest meeting notes and have them summarized
Search all pages mentioning a project and explain the context
Create a new page with today's meeting notes
Update an existing project status page with the latest updates

よくある質問

What tools does MCP server for LogSeq provide?

It provides seven tools: `list_graphs`, `list_pages`, `get_page_content`, `search`, `create_page`, `update_page`, and `delete_page`.

How do I configure LogSeq API settings?

You can add the environment variables `LOGSEQ_API_TOKEN` and `LOGSEQ_API_URL` directly in the MCP server configuration (JSON) or create a `.env` file in the working directory.

What are the default API settings?

The default API URL is `http://localhost:12315`. You must provide your own `LOGSEQ_API_TOKEN`.

How can I debug the server?

Use the MCP Inspector by running `npx @modelcontextprotocol/inspector uv --directory <path> run mcp-logseq`.

What runtime does this server require?

It is built with Python and uses `uv` as the package manager. The recommended way to run it is via `uvx mcp-logseq`.

「メモリとナレッジ」の他のコンテンツ

Neither MCP

stonianua

Project context your AI can query through MCP — with source evidence.

OpenLore

aakarim

Serve your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab

ctxfile

Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.

PLUR

plur-ai

AI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference

226

Groundwork

Rarefied-Earth

Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.