Skip to content

DocRaptor MCP by usefulapi

by usefulapi.io · remote · no sign-in to list tools · v1.16.3 · published by io.usefulapi

Turn HTML or a live URL into polished PDF and Excel files — hosted downloads, async jobs, history.

Deletes · 1
CompareRegistry entry

4 tools: 1 can delete or cancel things and 3 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http docraptor https://docraptor.usefulapi.io/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

4 tools

Deletes or cancels 1Claude Code: deny
  • docraptor_create_documentGenerate a PDF or Excel document from HTML (document_content) or a URL (document_url).No findings

    Why it is in this group

    • The name "docraptor_create_document" says "create": a word for a change.
    • The server marks it destructive (destructiveHint: true).
    Description, as the server wrote it
    Generate a PDF or Excel document from HTML (document_content) or a URL (document_url). Exactly one of document_content / document_url is required. By default the document is HOSTED and the tool returns a { download_url } you can fetch — ideal for agents (no large binary in the response). Set hosted:false to get the raw document back as base64, or async:true to enqueue a job and poll docraptor_get_document_status. IMPORTANT: real documents consume account credits (billed). Set test:true to generate a FREE, watermarked document while developing. DocRaptor API: POST /docs.

    Annotations the server declares

    • title: Create a document (PDF/XLS/XLSX)
    • destructiveHint: true
Only reads 3Claude Code: allow
  • docraptor_get_document_statusCheck the status of an asynchronous document created with docraptor_create_document({async:true}).No findings

    Why it is in this group

    • The name "docraptor_get_document_status" says "get": a word for reading.
    Description, as the server wrote it
    Check the status of an asynchronous document created with docraptor_create_document({async:true}). Returns status (queued | working | completed | failed), and when completed a download_url / download_id / number_of_pages. DocRaptor API: GET /status/{status_id}.

    Annotations the server declares

    • title: Get async document status
    • readOnlyHint: true
  • docraptor_list_documentsList metadata for documents created on this account, most recent first (paginated).No findings

    Why it is in this group

    • The name "docraptor_list_documents" says "list": a word for reading.
    Description, as the server wrote it
    List metadata for documents created on this account, most recent first (paginated). Note: DocRaptor does not retain the rendered files themselves — this returns metadata such as name, type, test flag, and creation time. DocRaptor API: GET /docs.json.

    Annotations the server declares

    • title: List documents
    • readOnlyHint: true
  • docraptor_list_ip_addressesList the IP addresses DocRaptor uses to fetch remote assets / document_url.No findings

    Why it is in this group

    • The name "docraptor_list_ip_addresses" says "list": a word for reading.
    Description, as the server wrote it
    List the IP addresses DocRaptor uses to fetch remote assets / document_url. Useful for allowlisting DocRaptor on a firewall or asset host. (DocRaptor notes these change over time — prefer HTTP Basic auth over IP allowlisting for securing assets.) DocRaptor API: GET /ips.json.

    Annotations the server declares

    • title: List DocRaptor IP addresses
    • readOnlyHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.16.3. Values in angle brackets are yours to fill in.

claude mcp add --transport http docraptor https://docraptor.usefulapi.io/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__docraptor__docraptor_get_document_status",
      "mcp__docraptor__docraptor_list_documents",
      "mcp__docraptor__docraptor_list_ip_addresses"
    ],
    "ask": [],
    "deny": [
      "mcp__docraptor__docraptor_create_document"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as docraptor. Review it before you use it.