{
  "id": "doc.pdf_to_xlsx",
  "object": "tool",
  "name": "PDF tables to Excel",
  "summary": "PDF tables into a workbook.",
  "description": "Finds the tables in a PDF with pdfplumber and writes them to an Excel workbook: one sheet per table, or one sheet per page with mode \"pages\". Numbers become real numbers and header rows are detected and frozen. Also returns a JSON index of every table (sheet, page, rows, columns). Needs a text layer; for scanned PDFs use doc.tables.",
  "category": "documents",
  "hosted_by": "Opentools",
  "runtime": "container",
  "side_effects": false,
  "status": "live",
  "credits": 3,
  "price": "$0.0030",
  "providers": [
    {
      "id": "opentools",
      "name": "Opentools",
      "price": "$0.0030"
    }
  ],
  "mcp_name": "doc_pdf_to_xlsx",
  "input_schema": {
    "type": "object",
    "properties": {
      "file": {
        "anyOf": [
          {
            "type": "object",
            "properties": {
              "url": {
                "type": "string",
                "format": "uri",
                "description": "Public http(s) URL of the file"
              }
            },
            "required": [
              "url"
            ]
          },
          {
            "type": "object",
            "properties": {
              "file_id": {
                "type": "string",
                "format": "uuid",
                "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
                "description": "An id returned by POST /v1/files"
              }
            },
            "required": [
              "file_id"
            ]
          },
          {
            "type": "object",
            "properties": {
              "base64": {
                "type": "string",
                "description": "Base64-encoded file bytes (up to 10 MB)"
              },
              "name": {
                "type": "string",
                "description": "File name, e.g. invoice.pdf"
              },
              "content_type": {
                "type": "string"
              }
            },
            "required": [
              "base64",
              "name"
            ]
          },
          {
            "type": "object",
            "properties": {
              "connection": {
                "type": "string",
                "minLength": 1,
                "maxLength": 64,
                "description": "A storage connection id or name (see storage.connections)"
              },
              "path": {
                "type": "string",
                "minLength": 1,
                "maxLength": 1024,
                "description": "Path of the file in that connection, e.g. reports/q3.pdf"
              }
            },
            "required": [
              "connection",
              "path"
            ]
          }
        ],
        "x-file": true,
        "description": "The PDF"
      },
      "pages": {
        "description": "Pages like \"1-3,5,8-\". All pages if omitted.",
        "type": "string",
        "maxLength": 500,
        "pattern": "^[\\d,\\s-]+$"
      },
      "tables": {
        "description": "Keep only these tables, by their 1-based position among the selected pages (see the index)",
        "maxItems": 100,
        "type": "array",
        "items": {
          "type": "integer",
          "minimum": 1,
          "maximum": 10000
        }
      },
      "mode": {
        "default": "tables",
        "description": "One sheet per table, or one sheet per page with its tables stacked",
        "type": "string",
        "enum": [
          "tables",
          "pages"
        ]
      },
      "header": {
        "default": "auto",
        "description": "Header rows: detect them, always treat the first row as one, or never",
        "type": "string",
        "enum": [
          "auto",
          "first",
          "none"
        ]
      },
      "strategy": {
        "default": "lines",
        "description": "lines finds ruled tables; text also finds tables aligned only by whitespace",
        "type": "string",
        "enum": [
          "lines",
          "text"
        ]
      }
    },
    "required": [
      "file"
    ]
  },
  "kind": "tool"
}