`document_text`

Pack: folketinget-dk · Connect: https://pipeworx.io/mcp (see Connect below for a single-pack URL)

No MCP client? Call it directly: GET https://gateway.pipeworx.io/v1/tools/document_text for the schema, then POST the same URL with its arguments for the data.

Return the full TEXT of a Folketinget (Danish Parliament) document by its numeric Dokument id — e.g. a minister’s final answer to a committee question (udvalgsspørgsmål), a bill text, a consultation reply. Resolves the Dokument record, fetches its published file and extracts the text (PDF or Word; the declared file format is not trusted, the bytes are sniffed). Returns title, date, the question wording (spørgsmålsordlyd), who answered/asked, the extracted text, and a reason when no text could be read (file missing, scanned image, unsupported type) so an empty text is never ambiguous. Long texts are paged with offset/max_chars. Source: Folketinget, parliamentary document register.

Parameters

Name	Type	Required	Description
`document_id`	number	yes	Numeric Dokument id, e.g. 1237262 (the id used by get_entity_by_id with entity “Dokument”).
`max_chars`	number	no	Max characters of text to return (default 100000, max 400000).
`offset`	number	no	Character offset into the extracted text, for paging a long document (default 0).

Example call

Arguments

{
  "document_id": 1237262
}

curl

curl -X POST https://gateway.pipeworx.io/folketinget-dk/mcp \
  -H 'Content-Type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"document_text","arguments":{"document_id":1237262}}}'

TypeScript (@pipeworx/sdk)

import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();

const result = await pipeworx.call('document_text', {
  "document_id": 1237262
});

More examples

{
  "document_id": 1236625,
  "max_chars": 20000
}

Response shape

Field	Type	Description
`found`	boolean	False when no document has that id
`document_id`	number
`title`	string \| null
`date`	string \| null
`type_id`	number \| null
`question_wording`	string \| null	Danish wording of the parliamentary question, when the document answers one
`question_title`	string \| null
`question_id`	number \| null
`answered_by`	string \| null
`actors`	array
`data_as_of`	string \| null
`source`	string
`file`	object
`text`	string \| null	Extracted document text; null when reason is set
`text_chars_total`	number
`offset`	number
`returned_chars`	number
`truncated`	boolean
`next_offset`	number \| null
`reason`	string	Why no text was returned (document_not_found, no_file, file_fetch_failed, file_blocked, no_extractable_text, unsupported_file_type, …)
`message`	string
`warnings`	array

Full JSON Schema

{
  "type": "object",
  "properties": {
    "found": {
      "type": "boolean",
      "description": "False when no document has that id"
    },
    "document_id": {
      "type": "number"
    },
    "title": {
      "type": [
        "string",
        "null"
      ]
    },
    "date": {
      "type": [
        "string",
        "null"
      ]
    },
    "type_id": {
      "type": [
        "number",
        "null"
      ]
    },
    "question_wording": {
      "type": [
        "string",
        "null"
      ],
      "description": "Danish wording of the parliamentary question, when the document answers one"
    },
    "question_title": {
      "type": [
        "string",
        "null"
      ]
    },
    "question_id": {
      "type": [
        "number",
        "null"
      ]
    },
    "answered_by": {
      "type": [
        "string",
        "null"
      ]
    },
    "actors": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "role": {
            "type": [
              "string",
              "null"
            ]
          },
          "name": {
            "type": [
              "string",
              "null"
            ]
          }
        },
        "additionalProperties": true
      }
    },
    "data_as_of": {
      "type": [
        "string",
        "null"
      ]
    },
    "source": {
      "type": "string"
    },
    "file": {
      "type": "object",
      "properties": {
        "title": {
          "type": [
            "string",
            "null"
          ]
        },
        "declared_format": {
          "type": [
            "string",
            "null"
          ]
        },
        "detected_format": {
          "type": "string"
        },
        "bytes": {
          "type": "number"
        },
        "pages": {
          "type": [
            "number",
            "null"
          ]
        }
      },
      "additionalProperties": true
    },
    "text": {
      "type": [
        "string",
        "null"
      ],
      "description": "Extracted document text; null when reason is set"
    },
    "text_chars_total": {
      "type": "number"
    },
    "offset": {
      "type": "number"
    },
    "returned_chars": {
      "type": "number"
    },
    "truncated": {
      "type": "boolean"
    },
    "next_offset": {
      "type": [
        "number",
        "null"
      ]
    },
    "reason": {
      "type": "string",
      "description": "Why no text was returned (document_not_found, no_file, file_fetch_failed, file_blocked, no_extractable_text, unsupported_file_type, ...)"
    },
    "message": {
      "type": "string"
    },
    "warnings": {
      "type": "array",
      "items": {
        "type": "string"
      }
    }
  },
  "additionalProperties": true
}

Connect

Add this to your MCP client config — every tool in the catalog, including this one — or use one-click install buttons:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://pipeworx.io/mcp"
    }
  }
}

Connect to just the folketinget-dk pack

{
  "mcpServers": {
    "folketinget-dk": {
      "url": "https://gateway.pipeworx.io/folketinget-dk/mcp"
    }
  }
}

See Getting Started for client-specific install steps.

document_text