Obsidian PublishをChatGPT、Claude、Geminiに接続

• 01 / 02ノートのメタデータを抽出する方法
• 02 / 02Markdownノートを読み取る方法

最速日

708ms

最遅日

1116ms

14日間の傾向

遅延傾向+30%

Obsidian Publish Connector

準備完了です。MCPクライアントを選択し、セットアップ手順に従ってください。

コネクタリンクhttps://edge.vinkius.com/vk_preview_2g0EdU9eeaIsXiKX4gDTqfxPUZ4owDXPPYajo4f3/mcpコピー

Claude Desktop

以下の手順で数秒で接続できます。

1. 1In Claude Desktop, open Settings → Connectors.
2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3. 3Click Add and start a new chat — Obsidian Publish capabilities are ready to use.

設定 · claude_desktop_config.jsonコピー

{
  "mcpServers": {
    "obsidian-publish-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_2g0EdU9eeaIsXiKX4gDTqfxPUZ4owDXPPYajo4f3/mcp"
    }
  }
}

• Claude
• ChatGPT
• Cursor
• VS Code
• Windsurf
• Claude Code
• JetBrains
• Cline

各クライアントの手順ガイドはこちらです。 接続方法

Claude向けのガイド付きセットアップ？ Obsidian PublishをClaudeや他のAIに設定する

このConnectorが対応するすべてのAIクライアントを見る ↑

• 01

  Researchers

  Use the agent to cross-reference characters or verify assertions from published research notes.

• 02

  Corporate Teams

  Build agents that read and summarize team SOPs stored in published vaults.

• 03

  Developers

  Pull technical architectures and code snippets from a digital garden directly into an IDE.

• 01

  Can I use this with private Obsidian vaults?

  Yes. You can connect to private vaults by providing an access token during setup.

• 02

  Which AI clients can use this MCP?

  Any MCP-compatible client, including Claude, Cursor, Windsurf, and VS Code.

• 03

  Do I need to host the MCP myself?

  No. Vinkius hosts and manages the MCP for you, so it is ready to use immediately.

• 04

  How does the agent know my note structure?

  The agent uses the navigation and file listing capabilities to map out your published vault's hierarchy.

• 05

  What information can the agent see?

  The agent can access raw markdown content, frontmatter, tags, and the site's navigation structure.

• 06

  Can the AI accurately recreate the folder structure of my vault?

  Yes. When the model invokes list_navigation, it downloads the systematic JSON map of the entire public vault, thereby allowing it to understand the relationships and physical structure of your folders perfectly.

• 07

  Does get_file automatically render complex Markdown components?

  No rendering is performed on our end. The get_file capability returns pure raw Markdown (including frontmatter and obsidian syntax). Fortunately, LLMs (like Claude) are exceptionally adept at reading and reasoning over raw Markdown text structures.

• 08

  If my Published site is private and requires a password, does it still work?

  Yes, it works gracefully. If you configured Obsidian Publish with restricted read access, you can manually inject a persistent token into the setup, giving your AI agent the clearance to read securely behind the authentication wall.

• 

  Notesnook (Private Note Taking & E2EE) AIコネクタ

  Manage encrypted notes via Notesnook — create secure entries, sync your vault, and audit private notebooks.

  表示
• 

  Mem AI (Knowledge Workspace) AIコネクタ

  Manage your knowledge base via Mem.ai — create notes, run AI semantic search, and organize collections.

  表示
• 

  Web Scraper AIコネクタ

  Equip your AI agent with the ability to search the web, read pages, extract metadata, and crawl sites as clean

  表示
• 

  GitScrum Knowledge AIコネクタ

  Build and query knowledge bases via GitScrum — manage notes as agent memory, maintain wiki pages, communicate

  表示

おすすめ

• 

  Markdown Frontmatter Harvester AIコネクタ

  Scan local Obsidian or Hugo vaults and extract all YAML frontmatter (tags, dates, status) into a single struct

  表示
• 

  Markdown Task Extractor AIコネクタ

  Instantly scan any local folder of Markdown notes (Obsidian, Notion, Logseq) and aggregate every scattered '-

  表示
• 

  Markdown HTML Compiler AIコネクタ

  Stop wasting AI tokens converting text. Compile Markdown into clean, minified HTML instantly for emails and CM

  表示
• 

  Goldsky (Web3 Data Indexing & Subgraphs) AIコネクタ

  Manage Web3 data pipelines and subgraphs. List, create, and monitor real-time indexing pipelines directly from

  表示