Paperless-ngxをChatGPT、Claude、Geminiに接続

• 01 / 02書類整理の方法
• 02 / 02ドキュメントを検索する

最速日

916ms

最遅日

1441ms

14日間の傾向

遅延傾向+16%

Paperless-ngx 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_ATPPyZ9x84oVznA3DvTkjjQfOt5pNtonNux3XF3j/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 — Paperless-ngx capabilities are ready to use.

設定 · claude_desktop_config.jsonコピー

{
  "mcpServers": {
    "paperless-ngx-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_ATPPyZ9x84oVznA3DvTkjjQfOt5pNtonNux3XF3j/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？ Paperless-ngx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

  在宅ワーカー

  公共料金の領収書、納税記録、取扱説明書などを、物理的な書類や膨大なフォルダから探す手間なく即座に見つけ出せます。

• 02

  法務・事務チーム

  特定の連絡先や文書タイプを照会し、レポート作成や情報の照合を迅速に行うことができます。

• 03

  研究者

  自動タグ付けとコンテンツ検索を活用して、大量のPDFや論文コレクションを効率的に管理できます。

• 01

  How do I connect my existing Paperless-ngx instance?

  You just need to provide your Paperless-ngx API URL and your Personal API Token in the Vinkius setup. Once connected, the MCP is ready to use in your AI client.

• 02

  Which AI clients can I use with this MCP?

  You can use any MCP-compatible client, including Claude, Cursor, and Windsurf.

• 03

  Can my agent see the text inside my PDFs?

  Yes. The agent can access the OCR text of your documents to perform searches and answer questions about the content.

• 04

  Is my data stored on Vinkius?

  Vinkius hosts the MCP and manages the connection, but the documents remain in your Paperless-ngx instance.

• 05

  Can I upload files through my AI agent?

  Yes, you can use the upload capability to add new documents directly to your archive via your agent.

• 06

  Can I search for documents using specific tags or date ranges?

  Yes. The list_documents capability allows you to filter by tags__id__in and created__date__gte. You can also perform a full-text search using the query parameter.

• 07

  Is it possible to see a preview of a document without downloading the whole file?

  Absolutely. Use the preview_document or thumb_document capabilities to get visual representations of the document content directly through the agent.

• 08

  Can I create new organization categories like tags or correspondents via AI?

  Yes, you have full management capabilities. You can use create_tag, create_correspondent, and create_document_type to organize your archive on the fly.

• 

  Internet Archive Search AIコネクタ

  Search 40M+ books, videos, audio, software across the Internet Archive.

  表示
• 

  Elastic Enterprise Search AIコネクタ

  Manage enterprise search via Elastic — search engines and documents, handle indexing, and monitor search analy

  表示
• 

  Milvus (Open-Source Vector Database) AIコネクタ

  Manage vector storage via Milvus — perform ANN searches, query scalar entities, and audit collections.

  表示
• 

  Typesense Vector Search AIコネクタ

  Automate vector similarity searches via Typesense — index documents, manage collections, and execute semantic

  表示

おすすめ

• 

  SEC EDGAR Filings — 10-K, 10-Q, 8-K, Insider Trades & Full-Text Search AIコネクタ

  Access all SEC filings: 10-K annual reports, 10-Q quarterly reports, 8-K material event disclosures, Form 4 in

  表示
• 

  Azure AI Search AIコネクタ

  Execute RAG queries against Azure AI Search natively — search vectors, full-text documents, and audit cloud in

  表示
• 

  Open-Source Strategy Economics AIコネクタ

  Calculate the economic impact and strategic value of open-source initiatives.

  表示
• 

  zrok (Open-Source Tunnel) AIコネクタ

  Securely share local resources with the world using zrok — manage environments, create public/private shares,

  表示