MCP.so
ログイン

Logseq MCP Tools

@joelhooks

リポジトリ

Logseq MCP Tools について

mcp server for logseq graph

基本情報

カテゴリ

メモリとナレッジ

ライセンス

NOASSERTION

ランタイム

node

トランスポート

stdio

公開者

joelhooks

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": {
    "logseq-mcp-tools": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "@joelhooks/logseq-mcp-tools",
        "--client",
        "claude"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Logseq MCP Tools?

Logseq MCP Tools is a Model Context Protocol (MCP) server that gives AI assistants like Claude structured access to your Logseq knowledge graph. It integrates with Logseq's HTTP API to retrieve pages, journal entries, backlinks, and perform graph analysis. Designed for Logseq users who want AI-powered exploration and summarization of their notes.

How to use Logseq MCP Tools?

Install via Smithery (npx -y @smithery/cli install @joelhooks/logseq-mcp-tools --client claude) or clone the repository, install dependencies, and configure your Logseq authentication token in a .env file. Start the server with npm start or npx tsx index.ts. Connect it to Claude Desktop, Cursor, the Anthropic API, or JetBrains Junie by adding the MCP configuration pointing to the built server.

Key features of Logseq MCP Tools

  • Retrieve a list of all Logseq pages
  • Get content and backlinks for any page
  • Generate journal summaries for flexible date ranges
  • Create and search pages in your graph
  • Analyze knowledge graph structure and gaps
  • Suggest connections between pages using AI
  • Execute natural language queries via DataScript

Use cases of Logseq MCP Tools

  • Ask an AI assistant to show your recent journal entries
  • Summarize notes from last week or any time range
  • Find all pages related to a specific topic
  • Discover missing or underdeveloped pages in your graph
  • Identify orphaned pages and potential connections

FAQ from Logseq MCP Tools

How do I get my Logseq authentication token?

Open Logseq, enable the HTTP API in Settings > Features, then set and copy your authentication token in Settings > Features > HTTP API Authentication Token. Place it in your .env file.

Does Logseq need to be running while using the server?

Yes, the MCP server communicates with Logseq via its HTTP API, so Logseq must be open and the HTTP API enabled.

What if Claude Desktop can't find Node.js?

Claude Desktop runs outside your shell environment. Install Node.js globally via Homebrew (brew install node) to ensure it is available to all applications.

How can I view logs for troubleshooting?

On macOS, monitor logs in real time with tail -n 20 -F ~/Library/Logs/Claude/mcp*.log. For detailed debugging, refer to the MCP debugging documentation.

What are the main dependencies?

The server is built using the Model Context Protocol TypeScript SDK, Zod for parameter validation, and the Logseq HTTP API for data access.

コメント

「メモリとナレッジ」の他のコンテンツ

RAG Documentation MCP Server

hannesrudolph

An MCP server implementation that provides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context.

267

Obsidian MCP Server

cyanheads

Read, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP.

618

Solomd

zhitongblog

A markdown editor — and the bridge to your LLM. Local-first, MIT, ~15 MB. Bundled MCP server lets Claude Code / Codex / Cursor drive your vault directly. 14 AI providers BYOK.

425

Semantic Scholar MCP Server

YUZongmin

A FastMCP server implementation for the Semantic Scholar API, providing comprehensive access to academic paper data, author information, and citation networks.

158

mcp-local-rag

nkapila6

"primitive" RAG-like web search model context protocol (MCP) server that runs locally. ✨ no APIs ✨

128