
Docling MCP
io.github.docling-project由 GitHub 帳號 docling-project 發布v3.5.0更新於 Nov 4, 2026
Convert PDFs and other documents to structured formats via Docling, for AI applications.
概覽
Docling MCP 可將 PDF 等文件轉換為結構化的 DoclingDocument JSON 或 Markdown,並讓助理產生新文件,支援本機或遠端 Docling Serve 轉換。
- 可以做什麼
- 將 PDF 等文件(本機檔案或網址)轉換為結構化的 DoclingDocument JSON
- 產生新文件:建立文件、加入標題、章節標題、段落與巢狀清單,並匯出為 Markdown 或儲存
- 將轉換或撰寫的文件匯出為 Markdown,圖片呈現方式可設定
- 在記憶體中快取已轉換文件以加快後續操作
- 轉換時可選擇啟用 OCR、表格結構辨識與視覺模型圖片描述
- 可選的 RAG 工具組,支援 LlamaIndex、LlamaStack 及 Milvus 上傳與檢索
- 適用情境
- 適合需要讓助理把 PDF 或掃描檔讀成結構化內容,用於摘要、資訊擷取或 RAG 流程的情境,也適合讓助理依 Docling 格式草擬文件並匯出為 Markdown。有 Docling Serve 執行個體時選遠端模式,需要離線轉換時選本機模式。
- 執行需求
- 以本機 Python 程序執行,通常透過 uvx 啟動。遠端模式(預設)需要 DOCLING_MCP_SERVICE_URL,通常還需 DOCLING_MCP_SERVICE_API_KEY 指向 Docling Serve 執行個體。本機模式需安裝 docling-mcp[local] 附加元件,且 OCR 引擎須安裝在轉換後端。可選 RAG 工具組需要 LLM 端點或 LlamaStack 伺服器。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 Docling MCP,將其新增到工作區。
- 為需要使用其工具的對話啟用該服務。
Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。
其他 MCP 客戶端
參照 儲存庫 中的啟動說明。
README
Docling MCP: making docling agentic
[CI] [PyPI version] [PyPI - Python Version] [uv] [Ruff] [Pydantic v2] [prek] [License MIT] [PyPI Downloads] [LF AI & Data] [MCP Registry] [docling-mcp MCP server] [MCP Toplist]
A document processing service using the Docling-MCP library and MCP (Model Context Protocol) for tool integration.
Overview
Docling MCP is a service that provides tools for document conversion, processing and generation. It uses the Docling library to convert PDF documents into structured formats and provides a caching mechanism to improve performance. The service exposes functionality through a set of tools that can be called by client applications.
Compatibility
If your MCP client application has not yet migrated to MCP SDK v2, pin:
See MIGRATION.md for the full migration guide.
Installation Options
Remote Mode (Recommended - Lightweight)
For users with access to Docling Serve API:
Getting Docling Serve: Visit docling-serve for installation guides. You can deploy it from published container images or look for managed Docling SaaS offerings.
Then configure your environment:
Local Mode (Full Features)
For users who need local conversion or don't have Docling Serve access:
Then configure your environment:
Hybrid Mode (Best of Both)
Install with local support and enable automatic fallback:
Configure for remote with fallback:
Features
- Conversion tools:
- PDF document conversion to structured JSON format (DoclingDocument)
- Generation tools:
- Document generation in DoclingDocument, which can be exported to multiple formats
- Local document caching for improved performance
- Support for local files and URLs as document sources
- Memory management for handling large documents
- Logging system for debugging and monitoring
- RAG applications with Milvus upload and retrieval
Configuration
All settings use the DOCLING_MCP_ prefix and can be supplied as environment
variables, in a .env file in the working directory, or via the env block of
your MCP client config. Copy .env.example as a starting point.
Conversion mode
Remote service (required when DOCLING_MCP_CONVERSION_MODE=remote)
Conversion pipeline (applies to both modes)
[!TIP] Enabling
DOCLING_MCP_DO_PICTURE_DESCRIPTION=trueadds a VLM inference step for every figure in the document. On resource-constrained hardware (e.g. a laptop running the model on CPU) this can significantly increase conversion time.
- Remote mode — increase
DOCLING_MCP_SERVICE_TIMEOUT(in seconds) to give the remote service enough time to complete. The default is300.0(5 minutes).- Local mode / MCP client timeout — the MCP client itself may also enforce a request timeout. For example, in LM Studio set the
timeoutfield (in milliseconds) in yourmcp.json:
Markdown export
Cache
LlamaIndex RAG (--tools llama-index-rag)
LlamaStack (--tools llama-stack-rag / --tools llama-stack-ie)
Setting variables in an MCP client config
Getting started
The easiest way to install Docling MCP and connect it to your client is by launching it via uvx.
Depending on the transfer protocol required, specify the argument --transport, for example
-
stdioused e.g. in Claude for Desktop and LM Studio -
sseused e.g. in Llama Stack -
streamable-httpused e.g. in containers setup
More options are available, e.g. the selection of which toolgroup to launch. Use the --help argument to inspect all the CLI options.
For developing the MCP tools further, please refer to the Developing section of CONTRIBUTING.md for instructions.
Integration with MCP clients
One of the easiest ways to experiment with the tools provided by Docling MCP is to leverage an AI desktop client with MCP support. Most of these clients use a common config interface. Adding Docling MCP in your favorite client is usually as simple as adding the following entry in the configuration file.
When using Claude for Desktop, simply edit the config file claude_desktop_config.json with the snippet above or the example provided here.
In LM Studio, edit the mcp.json file with the appropriate section or simply click on the button below for a direct install.
[Add MCP Server docling to LM Studio]
Other integrations are described in the integrations page.
Examples
Converting documents
Example of prompt for converting PDF documents:
Generating documents
Example of prompt for generating new documents:
Contributing
We welcome external contributions. See CONTRIBUTING.md for details on how to get started.
License
The Docling MCP codebase is under MIT license. For individual model usage, please refer to the model licenses found in the original packages.
LF AI & Data
Docling and Docling MCP is hosted as a project in the LF AI & Data Foundation.
IBM ❤️ Open Source AI: The project was started by the AI for knowledge team at IBM Research Zurich.
來源:README.md,提交 91e7c4f
工具
0版本歷史
5- v3.5.0最新Nov 4, 2026
- v3.4.0Oct 29, 2026
- v3.3.0Oct 6, 2026
- v3.2.1Sep 24, 2026
- v3.2.0Sep 16, 2026
評分
已滿足適用檢查項的 50%
該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。
- 近 30 天內可連通25 分
請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。
- 已宣告認證方式10 分
請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。
- 已列出工具15 分
請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。
- 描述必需15 分
- 圖示10 分
- 文件15 分
- 授權條款10 分