Docling MCP
Convert PDFs and other documents to structured formats via Docling, for AI applications.
Open the source (opens github.com) https://github.com/docling-project/docling-mcp
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
- Needs credentials: DOCLING_MCP_SERVICE_API_KEY. Use a key with the least access you can.
What it is
MCP servers from io.github.docling-project.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
pypi package (stdio)
docling-mcp@3.5.0
From the server's entry in the official MCP Registry
Settings it asks for
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.
Related
-
Docling by pagespool
MCP serversHosted Docling: convert PDF, Office files and images to Markdown and JSON, with OCR and tables.
-
flexible-graphrag
MCP serversGraphRAG, RAG, LlamaIndex, LangChain, 15 Prop Graph, 4 RDF, 10 Vector, 3 Search DBs. 14 data srcs, auto sync, Alfresco, Nuxeo, SharePoint, Box, CMIS, S3,GCS,Azure, web. KG auto-bld, Ontologies, 13 LLM providers, Docling, LlamaParse, LiteParse, Hybrid Search, AI Chat. TypeScript React, Vue, Angular, Python, REST, MCP, OpenArch, Langflow, CocoIndex.
git clone https://github.com/stevereiner/flexible-graphrag.git -
One MCP, many parsers
MCP serversOne MCP, many parsers. Routes between markitdown, Docling, and LlamaParse. Plus an interpret tool…
https://github.com/adelaidasofia/parse-mcp/releases/download/v0.1.0/parse-mcp.mcpb@0.1.0 -
GitHub MCP server
MCP serversGitHub's official MCP server. It lets an agent read and work with repositories, issues and pull requests.
https://api.githubcopilot.com/mcp/ -
Apify MCP server
MCP serversLets an agent run Apify's ready-made scrapers to pull data from websites, search engines, maps and social platforms.
-
Official MCP Registry
MCP serversThe MCP project's own registry of public MCP servers, so you can look for a connector before building one.