Smart OCR

Multi-provider AI OCR and structured JSON/table extraction API for PDFs, invoices, and receipts.

使うべきか

品質と安全性

A
説明の品質
100%
スキーマの完全性
93%
命名の品質
87%
ポイズニングのリスク
60%
権限の一致
100%
プロトコルへの準拠
100%

検出事項(3)

  • HIGHTool poisoning patterns detected
  • MEDIUMTool description contains URL to non-standard domainextract_document_json 内
  • MEDIUMTool description contains URL to non-standard domainget_smartocr_status 内

ツール定義とプロトコルへの準拠に関する自動分析に基づいています。

コンテキストコスト

~887トークン数(ツール定義)
~2.2 KB一般的なレスポンスサイズ
注意への影響は中程度(128k コンテキストの 0.69%)

これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。

インストール

ワンクリックインストール

これを `claude_desktop_config.json` ファイルに追加してください:

{
  "mcpServers": {
    "smartocr": {
      "url": "https://api.smartocr.dev/mcp"
    }
  }
}

リモートエンドポイント

https://api.smartocr.dev/mcpstreamable-http

できること

ツール一覧

ツール(3)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢extract_document_table(file_url, file_base64, file_name, preset, custom_headers, ...)

Extract structured table rows (line items, transactions, headers, document metadata, summary totals, Markdown table, and CSV) from a PDF or image (invoice, bank statement, credit card statement, receipt, timesheet, or scanned table). Works immediately on the free tier (2 free documents/day) or with an optional Smart OCR API key.

入力スキーマ

{
  "type": "object",
  "properties": {
    "file_url": {
      "type": "string",
      "description": "Public HTTP/HTTPS URL to a PDF, PNG, JPG, WEBP, or TIFF document to extract."
    },
    "file_base64": {
      "type": "string",
      "description": "Base64-encoded document content (raw base64 or data:...;base64,... URI). Provide either file_url or file_base64."
    },
    "file_name": {
      "type": "string",
      "description": "Optional filename with extension (e.g., \"invoice.pdf\", \"statement.pdf\", \"receipt.png\"). Defaults to \"document.pdf\"."
    },
    "preset": {
      "type": "string",
      "enum": [
        "auto",
        "invoice",
        "bank_statement",
        "receipt"
      ],
      "description": "Document preset: \"invoice\" for vendor invoices/bills, \"bank_statement\" for bank or credit card statements, \"receipt\" for retail/expense receipts, or \"auto\" to auto-detect."
    },
    "custom_headers": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Optional list of custom column headers to extract (e.g., [\"Date\", \"Description\", \"Amount\", \"Balance\"])."
    },
    "api_key": {
      "type": "string",
      "description": "Optional Smart OCR API key from https://smartocr.dev (can also be sent via x-api-key header). If omitted, uses the free tier (2 free docs/day)."
    }
  }
}
🟢extract_document_json(file_url, file_base64, schema, file_name, api_key)

Extract strict, structured JSON matching any custom JSON schema or field template from a PDF or image (PNG, JPG, WEBP, TIFF). Ideal for developer pipelines, ERP/accounting ingestion, and custom document fields. Works on the free tier (2 free docs/day) or with a Smart OCR API key (10 free credits at https://smartocr.dev).

入力スキーマ

{
  "type": "object",
  "properties": {
    "file_url": {
      "type": "string",
      "description": "Public HTTP/HTTPS URL to a PDF, PNG, JPG, WEBP, or TIFF document to extract."
    },
    "file_base64": {
      "type": "string",
      "description": "Base64-encoded document content (raw base64 or data:...;base64,... URI). Provide either file_url or file_base64."
    },
    "schema": {
      "type": "object",
      "description": "Target JSON schema or key-value object template describing the fields to extract (e.g., {\"vendorName\": \"string\", \"invoiceNumber\": \"string\", \"invoiceDate\": \"string\", \"totalAmount\": \"number\", \"lineItems\": [{\"description\": \"string\", \"quantity\": \"number\", \"amount\": \"number\"}]}).",
      "additionalProperties": true
    },
    "file_name": {
      "type": "string",
      "description": "Optional filename with extension (e.g., \"invoice.pdf\")."
    },
    "api_key": {
      "type": "string",
      "description": "Optional Smart OCR API key from https://smartocr.dev (can also be sent via x-api-key header). If omitted, uses the free tier (2 free docs/day)."
    }
  },
  "required": [
    "schema"
  ]
}
🟢get_smartocr_status(api_key)

Check Smart OCR service status, remaining free daily document quota (2 free documents/day), or developer API key credit balance, plus links to the web converter (https://read.smartocr.dev) and API portal (https://smartocr.dev).

入力スキーマ

{
  "type": "object",
  "properties": {
    "api_key": {
      "type": "string",
      "description": "Optional Smart OCR API key to check your remaining API credit balance."
    }
  }
}

コミュニティ

このサーバーを評価する

エビデンス

最近の観測

検証済みバージョンは記録されていませんツール 3 件