docling

docling is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from docling-project/docling-mcp. Its token cost is not measured, scanned A, original, MIT.

A local MCP server for Docling, a document-processing tool. Its setup runs the server from a specific project folder using the Python package manager uv.

In plain words
What is it for?
Use it to configure a local Docling MCP server. The input does not describe which document-processing actions the server exposes.
Why use it?
It provides the setup needed to start the Docling server locally, including the project directory it should use.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add mcp/docling-project/docling-mcp/integrations-docling
Clone the repo
git clone --depth 1 https://github.com/docling-project/docling-mcp

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for docling

README.md
[![agentmods](https://agentmods.dev/badge/mcp/docling-project/docling-mcp/integrations-docling.svg)](https://agentmods.dev/mcp/docling-project/docling-mcp/integrations-docling)
Your own site
<a href="https://agentmods.dev/mcp/docling-project/docling-mcp/integrations-docling"><img src="https://agentmods.dev/badge/mcp/docling-project/docling-mcp/integrations-docling.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

docling scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • docling — 100% identical, 0 lines differ
docs/integrations/claude_desktop_config.json · 11 lines

What it actually says

{
  "docling": {
    "command": "<use output of `which uv` in the `docling-mcp` folder>",
    "args": [
      "--directory",
      "<explicit path to docling-mcp or use output `pwd` in `docling-mcp` folder>",
      "run",
      "docling-mcp-server"
    ]
  }
}
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 11 lines scan A c859b5cf0288

Subscribe to this mod's changes

docling is an MCP server published in the GitHub repository docling-project/docling-mcp (732 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.