# docling-mcp

> docling-mcp — mk20mm-docling-mcp. Use this tool when you need to enhance text-only Large Language Models (LLMs) with document vision capabilities. The docling-mcp server converts PDFs, images, and Office files to Markdown, extracts tables, performs OCR, and enables RAG chunking, solving problems related to document understanding and data extraction. It takes in various file formats as input and outputs formatted Markdown text, ideal for use cases requiring automated document processing and analysis.

Canonical page: https://skillsregistry.net/skills/mk20mm-docling-mcp  
JSON: https://api.skillsregistry.net/v1/skills/mk20mm-docling-mcp

## Description

MCP server wrapping Docling to give text-only LLMs document vision via tools for converting PDFs, images, and Office files to Markdown, extracting tables, OCR, and RAG chunking.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/x57s6dw8ez)
- **Repository:** <https://github.com/mk20mm/docling-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "mk20mm-docling-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mk20mm-docling-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mk20mm-docling-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt