AffindaをChatGPT、Claude、Geminiに接続

• 01 / 03データの抽出方法
• 02 / 03ワークスペースの管理方法
• 03 / 03ステータス確認の方法

最速日

686ms

最遅日

1252ms

14日間の傾向

改善傾向-9%

Affinda 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_yFIGwqYMwMGDzAPprZCYJ7ppMcFfsuopOw4ljSHA/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 — Affinda capabilities are ready to use.

設定 · claude_desktop_config.jsonコピー

{
  "mcpServers": {
    "affinda-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_yFIGwqYMwMGDzAPprZCYJ7ppMcFfsuopOw4ljSHA/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？ Affinda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

  採用チーム

  履歴書のスクリーニングを自動化し、候補者のメタデータを手間なく抽出できます。

• 02

  経理部門（AP）

  請求書データの抽出を監査し、AIを利用して支払い詳細を検証できます。

• 03

  オペレーションマネージャー

  文書処理ワークフローを監視し、ワークスペースの設定を一元管理できます。

• 04

  コンプライアンス担当者

  リスク評価や検証のために、解析された身分証明書などの文書を取得できます。

• 01

  What types of documents can I parse?

  The MCP supports parsing several document types, including resumes, invoices, receipts, and passports. You can also upload general PDFs or images for data extraction.

• 02

  Is the data I get structured?

  Yes. The goal is to move beyond simple text extraction. The MCP provides structured JSON data, which means the information is organized and ready for immediate use in your applications.

• 03

  How do I check if a document finished processing?

  You can use the capabilities to list documents in a workspace, which shows the current processing status. You can also retrieve the specific document data using its ID.

• 04

  Do I need to know the document type beforehand?

  No. You can first use the capability to list all document types your account supports, or simply try to parse a document, and the system will guide you.

• 05

  Does this work with my existing document storage?

  This MCP handles the parsing and extraction process. You manage the document storage and use the MCP to pull the structured data from it.

• 06

  How do I find my Affinda API Key?

  Log in to Affinda, click on your profile avatar, and go to Settings > API Keys. You can generate a new token there. Remember to copy it immediately, as it is only shown once.

• 07

  What document types are supported?

  Affinda supports dozens of specialized models including Resumes, Invoices, Receipts, Passports, Driver Licenses, and Purchase Orders. Use the list_document_types capability to see the full list for your account.

• 08

  Can I parse a document via a public URL?

  Yes! The create_document capability accepts a url parameter. Simply provide the direct link to the PDF or image, and Affinda will retrieve and parse it automatically.

• 

  PDF Invoice Data Extractor AIコネクタ

  Extract raw text directly from digital PDF invoices entirely local. Keeps your sensitive accounting data air-g

  表示
• 

  Extracta AIコネクタ

  Automate data extraction via Extracta — process documents into structured JSON, handle AI classification, and

  表示
• 

  DocSumo AIコネクタ

  Equip your AI agent to automate document data extraction, manage IDP workflows, and audit processed files via

  表示
• 

  Parseur AIコネクタ

  Automate document processing via Parseur — list mailboxes, upload PDFs/Emails, extract structured data pipelin

  表示

おすすめ

• 

  Import.io (Web Data Extraction) AIコネクタ

  Extract structured data from any website via Import.io — run extractors, manage bulk crawls, and monitor API u

  表示
• 

  Data Pipeline Prover AIコネクタ

  A data team asked an AI to build an ETL pipeline. No schema contract. No idempotency. No freshness SLA. The pi

  表示
• 

  Sensible AIコネクタ

  Extract structured data from PDFs, images, and documents using Sensible's powerful document parsing engine.

  表示
• 

  Docparser AIコネクタ

  Equip your AI agent to extract data from documents, manage parsers, and track extraction results via the Docpa

  表示