This MCP server converts PDFs and other documents into structured formats using Docling, targeting AI applications. The project description indicates document-to-structure processing as its core capability.
🛠️ Key Features
Converts PDFs and other documents to structured formats via Docling.
Exposes functionality through an MCP server.
🚀 Use Cases
Feeding AI applications with structured representations derived from document inputs.
⚡ Developer Benefits
Integrates document conversion with AI workflows that consume structured data.
⚠️ Limitations
No additional operational details (e.g., supported formats beyond “PDFs and other documents,” configuration options, or output schema) are provided in the available source excerpt.
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
docling-mcp
MCP Python SDK
>=3.0.0
mcp>=2.0.0
>=2.0.0,<3.0.0
mcp>=1.9.4,<2.0.0
If your MCP client application has not yet migrated to MCP SDK v2, pin:
Getting Docling Serve: Visit docling-serve for installation guides. You can deploy it from published container images or look for managed Docling SaaS offerings.
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
Variable
Default
Description
DOCLING_MCP_CONVERSION_MODE
remote
remote or local
Remote service (required when DOCLING_MCP_CONVERSION_MODE=remote)
Variable
Default
Description
DOCLING_MCP_SERVICE_URL
—
URL of the Docling Serve instance
DOCLING_MCP_SERVICE_API_KEY
—
API key for the service
DOCLING_MCP_SERVICE_TIMEOUT
300.0
Timeout in seconds for a whole conversion job
DOCLING_MCP_SERVICE_MAX_RETRIES
3
Max retry attempts
DOCLING_MCP_FALLBACK_TO_LOCAL
false
Fall back to local if service is unreachable (requires docling-mcp[local])
Conversion pipeline (applies to both modes)
Variable
Default
Description
DOCLING_MCP_KEEP_IMAGES
false
Retain page images in output
DOCLING_MCP_IMAGES_SCALE
1.0
Image scale factor (increase to avoid tensor padding errors)
DOCLING_MCP_DO_OCR
true
Run OCR pipeline
DOCLING_MCP_OCR_ENGINE
auto
OCR engine by its docling engine kind: auto, easyocr, tesseract (system binary), tesserocr (Python bindings), ocrmac, rapidocr. The engine must be installed on the conversion backend. In remote mode it is sent as the Docling Serve ocr_preset, so server-defined preset names also work there
DOCLING_MCP_OCR_LANG
—
Comma-separated OCR languages, passed to the engine unchanged. iso:en,iso:de works with any engine (docling ≥ 2.127, recommended with auto); bare codes are engine-specific (eng for Tesseract, en for EasyOCR or Docling Serve). Unset means the engine's defaults
DOCLING_MCP_DO_TABLE_STRUCTURE
true
Detect table structure
DOCLING_MCP_DO_PICTURE_DESCRIPTION
false
Run a vision-language model to generate textual descriptions for figures and pictures
DOCLING_MCP_PICTURE_DESCRIPTION_PRESET
—
Preset ID for the picture-description VLM (e.g. smolvlm, granite_vision). When unset the backend default is used. Only applies when DOCLING_MCP_DO_PICTURE_DESCRIPTION=true
TIP
Enabling DOCLING_MCP_DO_PICTURE_DESCRIPTION=true adds 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 is 300.0 (5 minutes).
Local mode / MCP client timeout — the MCP client itself may also enforce a request timeout. For example, in LM Studio set the timeout field (in milliseconds) in your mcp.json:
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.
Other integrations are described in the integrations page.
Examples
Converting documents
Example of prompt for converting PDF documents:
prompt
Convert the PDF document at <provide file-path> into DoclingDocument and return its document-key.
Generating documents
Example of prompt for generating new documents:
prompt
I want you to write a Docling document. To do this, you will create a document first by invoking `create_new_docling_document`. Next you can add a title (by invoking `add_title_to_docling_document`) and then iteratively add new section-headings and paragraphs. If you want to insert lists (or nested lists), you will first open a list (by invoking `open_list_in_docling_document`), next add the list_items (by invoking `add_list_items_to_list_in_docling_document`). After adding list-items, you must close the list (by invoking `close_list_in_docling_document`). Nested lists can be created in the same way, by opening and closing additional lists.
During the writing process, you can check what has been written already by calling the `export_docling_document_to_markdown` tool, which will return the currently written document. At the end of the writing, you must save the document and return me the filepath of the saved document.
The document should investigate the impact of tokenizers on the quality of LLMs.
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.
Set to 'false' to disable the OCR pipeline. Default: true.
DOCLING_MCP_OCR_ENGINE
OCR engine kind: 'auto' (default), 'easyocr', 'tesseract', 'tesserocr', 'ocrmac', 'rapidocr'. Must be installed on the conversion backend.
DOCLING_MCP_OCR_LANG
Comma-separated OCR languages (e.g. 'iso:en,iso:de' or 'eng,deu'). When unset the engine's default languages apply.
DOCLING_MCP_DO_TABLE_STRUCTURE
Set to 'false' to disable table structure detection. Default: true.
DOCLING_MCP_DO_PICTURE_DESCRIPTION
Set to 'true' to run a vision-language model to generate textual descriptions for figures and pictures. Requires a VLM to be available on the conversion backend. Default: false.
DOCLING_MCP_PICTURE_DESCRIPTION_PRESET
Preset ID for the picture-description VLM (e.g. 'smolvlm', 'granite_vision'). When unset the backend default is used. Only applies when DOCLING_MCP_DO_PICTURE_DESCRIPTION=true.
DOCLING_MCP_IMAGE_EXPORT_MODE
Controls how images are rendered when exporting to Markdown. Accepted values: 'placeholder' (default, emits <!-- image -->), 'embedded' (base64 data-URI), 'referenced' (file path / URL).
DOCLING_MCP_CACHE_MAX_DOCUMENTS
Maximum number of documents to keep in the in-memory cache. Oldest (least-recently-used) documents are evicted when the limit is reached. Default: 10.