InnerVault

Docling MCP

Stale Official MCP Registry, io.github.docling-project

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_KEY secret · 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

  1. Docling by pagespool

    MCP servers

    Hosted Docling: convert PDF, Office files and images to Markdown and JSON, with OCR and tables.

    Stale Official MCP Registry, com.pagespool Updated 12 days ago 1 note

  2. flexible-graphrag

    MCP servers

    GraphRAG, 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.

    Stale GitHub, stevereiner 199 ★Apache-2.0Updated 5 days ago

    git clone https://github.com/stevereiner/flexible-graphrag.git
  3. One MCP, many parsers

    MCP servers

    One MCP, many parsers. Routes between markitdown, Docling, and LlamaParse. Plus an interpret tool…

    Stale Official MCP Registry, io.github.adelaidasofia Updated 6 months ago 2 notes

    https://github.com/adelaidasofia/parse-mcp/releases/download/v0.1.0/parse-mcp.mcpb@0.1.0
  4. GitHub MCP server

    MCP servers

    GitHub's official MCP server. It lets an agent read and work with repositories, issues and pull requests.

    Hand-checked InnerVault (hand-checked), GitHub 34.3k ★MIT

    https://api.githubcopilot.com/mcp/
  5. Apify MCP server

    MCP servers

    Lets an agent run Apify's ready-made scrapers to pull data from websites, search engines, maps and social platforms.

    Hand-checked InnerVault (hand-checked), Apify 16.0k ★MIT

  6. Official MCP Registry

    MCP servers

    The MCP project's own registry of public MCP servers, so you can look for a connector before building one.

    Hand-checked InnerVault (hand-checked), MCP project Moving from MIT to Apache-2.0