Docling MCP
Convert PDFs and other documents to structured formats via Docling, for AI applications.
Connect
Review any command before running it. Package names and URLs come from the server's own registry entry.
Package (pypi 3.5.0)
uvx docling-mcp
Or add to your MCP client config:
{
"mcpServers": {
"docling-mcp": {
"command": "uvx",
"args": [
"docling-mcp"
],
"env": {
"DOCLING_MCP_SERVICE_API_KEY": "<YOUR_VALUE>"
}
}
}
}
DOCLING_MCP_CONVERSION_MODE— Conversion mode: 'remote' (default) or 'local' (requires docling-mcp[local] extra).DOCLING_MCP_SERVICE_URL— Base URL of the Docling Serve instance. Required when conversion mode is remote.DOCLING_MCP_SERVICE_API_KEYsecret — API key for authenticating with Docling Serve.DOCLING_MCP_SERVICE_TIMEOUT— Request timeout in seconds for the remote Docling Serve API. Default: 300.0.DOCLING_MCP_SERVICE_MAX_RETRIES— Maximum number of retry attempts for remote API requests. Default: 3.DOCLING_MCP_FALLBACK_TO_LOCAL— Set to 'true' to fall back to local conversion when Docling Serve is unreachable.DOCLING_MCP_KEEP_IMAGES— Set to 'true' to retain page images in converted documents. Default: false.DOCLING_MCP_IMAGES_SCALE— Image scale factor (e.g. 1.0, 2.0). Increase to avoid tensor batching errors. Default: 1.0.DOCLING_MCP_DO_OCR— 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.
This server takes extra arguments — see its repository.
Related servers
REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
browser-use
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
paperclip
Trending hip-hop artist momentum scores across four cultural dimensions.
World Monitor
Real-time global intelligence on conflict, markets, energy, trade, shipping and cyber. 102 tools.
Ruflo
Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.
Front-End Checklist
Review frontend code and live pages against 386 quality-gated web development rules.
Data from the Official MCP Registry