为您的 AI 助手提供文档处理超能力

Connect AI agents to Documentize with MCP

The Documentize MCP server exposes all document processing capabilities as tools for AI agents and LLM clients — convert, merge, extract, sign, and more, directly from Claude Desktop, VS Code Copilot, Cursor, or any MCP-compatible host.

⚡ 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"
    }
  }
}

Restart Claude Desktop. The Documentize tools will appear in the tool list.

🔌 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"
    }
  }
}

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.
  2. Call GetTaskStatus with that task ID and poll until statusCode is 200.
  3. Use the downloadURL from the status response to retrieve the result.
// 1. Start a task
ConvertDocument(fileUrl: "https://example.com/report.pdf",
                inputType: "pdf", outputType: "docx")
// → { "folderName": "abc123", "statusCode": 202 }

// 2. Poll
GetTaskStatus(taskId: "abc123")
// → { "statusCode": 200, "downloadURL": "https://..." }

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

🧰 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 must be public URLs accessible from the server (no local paths).
  • 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.

Quick Reference

MCP Endpoint

https://api.documentize.app/mcp

claude_desktop_config.json

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

.vscode/mcp.json

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

Key Facts

  • Protocol: MCP 2025-11-25 (Streamable HTTP)
  • Sessions: stateful — Mcp-Session-Id header required after init
  • Tasks are async — poll GetTaskStatus for the download link
  • All file inputs must be public URLs

将 Claude、Cursor 或任何兼容 MCP 的客户端连接至 28+ 文档工具。转换、压缩、签名、提取文本、运行 OCR,并生成 AI 摘要——全部通过自然语言完成。

Documentize MCP 工作原理

1. 连接您的 MCP 客户端

将 Documentize MCP 服务器添加到 Claude Desktop、Cursor、VS Code 或任何兼容 MCP 的客户端。仅需一行配置。

2. 初始化会话

您的客户端自动发送初始化请求并获取会话 ID。所有后续调用都使用此会话进行跟踪(非常适合基于使用量的变现)。

3. 自然提问

“将此 PDF 转换为 DOCX” — 您的 AI 助手使用您的文档调用相应工具。无需 API 文档。

4. 获取结果

服务器异步处理,轮询状态,并将转换后的文档或提取的数据直接交付给您的 AI 助手。

FAQs

模型上下文协议(MCP)是一项开放标准,允许 Claude、Cursor 等 AI 助手直接调用工具。无需编写 API 代码,只需自然地提问即可。Documentize 提供了一个 MCP 服务器,内置 28 种文档处理工具,您的 AI 可以立即使用。
有状态模式支持每个会话的跟踪、使用计量和客户端隔离——这对实现盈利至关重要。每个客户端在初始化后会获得唯一的会话 ID,您可以依据该 ID 按使用量计费、强制速率限制或跟踪客户活动。您的 AI 客户端会自动处理会话 ID。
是的!使用 file:// URI(例如 file:///home/user/document.pdf)。您的 MCP 客户端会发送文件路径,Documentize 会直接从本地文件系统读取文件。非常适合不应上传到云端的敏感文档。
Claude Desktop(带代理模式)、Cursor IDE、带 Copilot 的 VS Code、Continue.dev,以及任何兼容 MCP 的客户端。我们还提供直接的 HTTP 接口以便自定义集成。
Documentize 在自行托管时运行在您自己的基础设施上,或在我们的欧盟服务器上运行云版。对于 MCP 服务器,您可以选择:自行托管以实现完整的数据控制,或使用我们的云 API 以获得便利。文档数据绝不会被用于训练 AI 模型。
Documentize 提供处理引擎。您可以添加身份验证中间件、使用跟踪和计费。状态会话模型为您提供可关联到 API 密钥或用户账户的 Mcp-Session-Id 标头。我们提供商业再分发的许可。

Unlock the Power of Document Management

深度分层 SVG 架构

每个 SVG 由背景层、中景层和前景层组成,具备 Z-index 排序和依赖追踪。AI 管理层级关系,并自动移除表现不佳的层,以保持输出的整洁和连贯。

迭代式 SVG 编辑

通过持续的 AI 对话改进和修改 SVG 设计。

快速矢量创建

在几秒钟内创建图标、徽标和插图。

简洁,基于使用量的定价

免费套餐

$0
  • 每月 50 次文档操作
  • 全部 28 项 MCP 工具
  • 社区支持
  • 速率限制:5 次请求/分钟

专业版

$49
  • 每月 2,000 次操作
  • 优先处理队列
  • 邮件支持
  • 速率限制:每分钟 30 次请求
  • 使用分析仪表板

企业版

定制
  • 无限操作
  • 专用基础设施选项
  • SLA 保证(99.9%)
  • 单点登录与团队管理
  • 自定义工具开发