Mmcp.market

Docling MCP server

by docling-project·io.github.docling-project/docling-mcp·v3.2.0
No reviews yet

Convert PDFs and other documents to structured formats via Docling, for AI applications.

A85/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A85/100

full report

Adoption
Growing

750 stars

Reviews

Write one

Nobody has reviewed Docling MCP yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Docling MCP tools (23, 4 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • add_list_items_to_list_in_docling_document

    Add list items to an open list in an existing document in the local document cache.

  • add_paragraph_to_docling_document

    Add a paragraph of text to an existing document in the local document cache.

  • add_section_heading_to_docling_document

    Add a section heading to an existing document in the local document cache.

  • add_table_in_html_format_to_docling_document

    Add an HTML-formatted table to an existing document in the local document cache.

  • add_title_to_docling_document

    Add or update the title of a document in the local document cache.

  • close_list_in_docling_document

    Closes a list group in an existing document in the local document cache.

  • convert_directory_files_into_docling_document

    Convert all files from a local directory path and store them in local cache.

  • convert_document_into_docling_document

    Convert a document of any type from a URL or local path and store in local cache.

  • create_new_docling_documentwrite action

    Create a new Docling document from a provided prompt string.

  • delete_document_items_at_anchorswrite action

    Delete multiple document items identified by their anchors.

  • export_docling_document_to_markdown

    Export a document from the local document cache to markdown format.

  • export_docling_document_to_vector_db

    Exports a document from the local document cache to a vector database for search capabilities.

  • get_overview_of_document_anchors

    Retrieve a structured overview of a document from the local document cache.

  • get_text_of_document_item_at_anchor

    Retrieve the text content of a specific document item identified by its anchor.

  • information_extraction

    Information extraction from a document.

  • insert_document_to_vectordbwrite action

    Insert the document in the vectordb.

  • is_document_in_local_cache

    Verify if a Docling document is already converted and in the local cache.

  • open_list_in_docling_document

    Open a new list group in an existing document in the local document cache.

  • page_thumbnail

    Generate a thumbnail image for the requested page.

  • save_docling_document

    Save a document from the local document cache to disk in both markdown and JSON formats.

  • search_documents

    Searches through previously uploaded and indexed documents using semantic search.

  • search_for_text_in_document_anchors

    Search for specific text and keywords within a document's anchors.

  • update_text_of_document_item_at_anchorwrite action

    Update the text content of a specific document item identified by its anchor.

Public scan report

scanner v0.1.9 · 2026-09-20 · same rubric, same numbers if you re-run it

no findings
  • Code scan32 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 13 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10
Overall 85/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

What the publisher says

From the Docling MCP repository's README, as published. We do not edit it. Read it on GitHub

Docling MCP: making docling agentic

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:

pip install "docling-mcp<3.0.0"

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.

pip install docling-mcp

Then configure your environment:

export DOCLING_MCP_SERVICE_URL=https://your-docling-service.example.com
export DOCLING_MCP_SERVICE_API_KEY=your-api-key-here
export DOCLING_MCP_CONVERSION_MODE=remote

Local Mode (Full Features)

For users who need local conversion or don't have Docling Serve access:

pip install docling-mcp[local]

Then configure your environment:

export DOCLING_MCP_CONVERSION_MODE=local

Hybrid Mode (Best of Both)

Install with local support and enable automatic fallback:

pip install docling-mcp[local]

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Install directly

claude mcp add docling-mcp -- uvx docling-mcp
Add to Cursor

Docling MCP: common questions

Is Docling MCP server safe?
Yes, by our scan: it is graded A (85/100). Read the Docling MCP safety report
How do I install Docling MCP?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does Docling MCP need an API key?
Yes. The registry entry asks for DOCLING_MCP_SERVICE_API_KEY.
Is Docling MCP maintained?
The last commit was 14 days ago (2026-09-07). The latest release is v3.2.0.

More from docling-project →