Суперспособности обработки документов для вашего AI‑ассистента

⚡ Endpoint

The MCP server runs over Streamable HTTP at:

https://api.documentize.app/mcp

The server uses stateful sessions. After the initial initialize request the server returns an Mcp-Session-Id header; include it in every subsequent request. MCP clients handle this automatically.

🔌 Connect from Claude Desktop

Add the server to claude_desktop_config.json (%APPDATA%\Claude\ on Windows, ~/Library/Application Support/Claude/ on macOS):

{
  "mcpServers": {
    "documentize": {
      "type": "http",
      "url": "https://api.documentize.app/mcp",
      "headers": {
        "Authorization": "Bearer dmk_your_key_here"
      }
    }
  }
}

Restart Claude Desktop. The Documentize tools will appear in the tool list. Omit the headers block to connect anonymously — the tools still work, but under the anonymous daily limit.

🔌 Connect from VS Code (GitHub Copilot)

Create .vscode/mcp.json in your workspace (or add to User Settings):

{
  "servers": {
    "documentize": {
      "type": "http",
      "url": "https://api.documentize.app/mcp",
      "headers": {
        "Authorization": "Bearer dmk_your_key_here"
      }
    }
  }
}

Open GitHub Copilot Chat, switch to Agent mode, and click the Tools button — Documentize tools will be listed there.

🔌 Connect from Cursor / Cline

In Cursor, open Settings → MCP and add a new server:

{
  "name": "documentize",
  "type": "http",
  "serverUrl": "https://api.documentize.app/mcp"
}

Cline users can add the same entry under MCP Servers in its settings panel.

⚙️ How tasks work

All processing tools are asynchronous. Each call starts a background job and returns a JSON object with a folderName field — that is your task ID.

1. Call a processing tool (e.g. ConvertDocument) → receive a task ID (folderName).
2. Call GetTaskStatus with that task ID and poll until statusCode is 200.
3. When complete, the response contains a sharedFiles array. Each entry has a fileName (display name) and an uploadFileName (a pre-signed S3 download URL). Open any uploadFileName URL in your browser to download the result file.

// 1. Start a task
ConvertDocument(fileUrl: "https://example.com/report.pdf",
                inputType: "pdf", outputType: "docx")
// → { "folderName": "abc123", "statusCode": 204 }

// 2. Poll until done (statusCode 204/202/203 = still processing)
GetTaskStatus(taskId: "abc123")
// → {
//     "statusCode": 200,
//     "sharedFiles": [
//       {
//         "fileName": "report.docx",
//         "uploadFileName": "https://s3.amazonaws.com/...presigned-url..."
//       }
//     ]
//   }

// 3. Download the result
// Open uploadFileName in a browser, or tell the agent:
//   "Download https://s3.amazonaws.com/...presigned-url... and save it as report.docx"

Use GetNextAppSuggestions after any operation to get recommended follow-up tools based on the output format.

📂 Providing your files

The MCP server accepts files in three ways — use whichever fits your workflow:

Local file path (recommended for desktop AI clients)

When running Claude Desktop, Cursor, or Cline on your own machine, simply pass the path to a file on your disk. The AI agent reads it directly — no manual upload needed.

// Windows absolute path
ConvertDocument(fileUrl: "C:\\Users\\Alice\\Documents\\report.pdf",
                inputType: "pdf", outputType: "docx")

// macOS / Linux absolute path
ConvertDocument(fileUrl: "/home/alice/documents/report.pdf",
                inputType: "pdf", outputType: "docx")

You can also use the standard file:// URI format:

// file:// URI — Windows
ConvertDocument(fileUrl: "file:///C:/Users/Alice/Documents/report.pdf",
                inputType: "pdf", outputType: "docx")

// file:// URI — macOS / Linux
ConvertDocument(fileUrl: "file:///home/alice/documents/report.pdf",
                inputType: "pdf", outputType: "docx")

Remote URL

Pass any publicly accessible https:// or http:// URL. The server fetches the file automatically before processing.

ConvertDocument(fileUrl: "https://example.com/report.pdf",
                inputType: "pdf", outputType: "docx")

Practical agent prompts

With a local AI client you can refer to files by name and let the agent resolve the path:

// In Claude Desktop or Cursor chat:
"Convert my file C:\Users\Alice\Downloads\invoice.pdf to Word format"

"Compress /home/alice/thesis.pdf and send me the download link"

"Extract all text from file:///C:/Reports/Q1.pdf"

🧰 Available Tools

Document Operations

• ConvertDocument — Convert between PDF, DOCX, PPTX, HTML, JPG, PNG, and more.
• MergeDocuments — Combine multiple files into a single document.
• SplitDocument — Split a PDF by page ranges, bookmarks, or fixed size.
• CompressDocument — Reduce PDF file size (low / medium / high).
• RotateDocument — Rotate all or selected pages by 90°, 180°, or 270°.
• ResizeDocument — Resize PDF pages to A4, Letter, A3, etc.
• RemovePages — Delete specific pages from a PDF.

Security

• LockDocument — Encrypt a PDF with a password.
• UnlockDocument — Remove a password from a protected PDF.
• SignDocument — Digitally sign a document.
• VerifySignature — Verify existing digital signatures.

Content Extraction

• ExtractText — Pull all text from a document (Pure or Raw mode).
• ExtractImages — Export all embedded images.
• ExtractMetadata — Read author, title, creation date, keywords, etc.
• ExtractFormData — Export data from fillable PDF form fields.
• ParseDocument — Parse annotations, bookmarks, tables, and more.
• SearchInDocument — Find text occurrences inside a document.
• MakeSearchable — Add a text layer to a scanned PDF via OCR.
• RunOcr — Run OCR on a scanned file or image to produce a searchable PDF.

Form & Structure

• FlattenDocument — Flatten form fields and annotations (make non-editable).
• AddTable — Embed a table from an Excel or CSV file into a PDF.
• AddToc — Add a table of contents to a PDF based on its headings.

AI-Powered

• GenerateTableOfContents — AI-structured TOC from document headings.
• GenerateAbstract — Summarize a document (academic / professional / casual style).
• GenerateChecklist — Extract tasks, requirements, or compliance items from a document.
• AnalyzeResume — Extract, analyze, or compare a CV against a job description.
• ChatWithDocument — Ask questions about document content (RAG).
• GenerateSvg — Create an SVG illustration from a text prompt.
• AddIllustrations — Generate AI illustrations and embed them in a document.

Status & Utility

• GetTaskStatus — Check task progress; returns download link when ready.
• GetNextAppSuggestions — Get recommended follow-up operations for a given output.

📋 Notes

• File sources can be a local path (C:\file.pdf, /home/user/file.pdf), a file:// URI, or a public https:// URL.
• For MergeDocuments, pass file URLs as a comma-separated string.
• Status codes: 202/203 = still processing, 200 = done, 500 = error.
• MCP protocol version reported by the server: 2025-11-25.
• OAuth: the server publishes protected-resource metadata at /.well-known/oauth-protected-resource/mcp and answers unauthorized requests with WWW-Authenticate: Bearer resource_metadata="…", so clients implementing MCP authorization sign you in through the browser.
• Authentication is optional but recommended: send Authorization: Bearer dmk_… to have calls counted against your account instead of the anonymous limit. Keys are created above, shown once, and can be revoked at any time.