FRENES

Files and documents · MCP server

Docling.rs: MCP server, setup and security

Docling.rs is an open-source MCP server that lets an AI agent convert PDFs Office documents HTML and scans into Markdown for agents. Its repository has 111 stars and its last commit is from October 24, 2026 and it is licensed under MIT.

Actively maintainedSystem access

What Docling.rs does

According to its repository: “Documents to Markdown for agents: PDF layout, tables and OCR, Office, HTML, scans. docling in Rust.”

An MCP server gives an AI agent extra tools it calls during the conversation: the agent reads their description, decides to use them and gets the result back. Docling.rs is listed under Files and documents, a category of 55 servers in the directory, where it ranks #20 by stars.

Topics declared by the repository: autogen, docling, langchain, langgraph, markdown, pdf.

Installing and connecting Docling.rs

Distribution modes declared in the official MCP registry:

  • PyPI package (Python, started with uvx or pip)
  • Docker (OCI) image

Like any MCP server, you declare it in your client's configuration (Claude Desktop, Claude Code, Cursor, VS Code, Codex…): a name, the command that starts it or its URL, and any environment variables. The client then starts it and lists its tools. Project language: Rust.

Security: what to check

An MCP server runs code with the rights you give it, and the model reads its tool descriptions: a malicious or compromised server can hijack the agent. Read the code, or pick a maintained and widely used server, before connecting it.

Points found for Docling.rs:

  • System access: the Files and documents category gives the agent control over files, a terminal, code or a browser. A booby-trapped instruction in content the agent reads (prompt injection) can then turn into an action.

Good practice: grant only the rights needed (least privilege), require human approval for irreversible actions, and run the AI agent security check.

Project activity and maintenance

Created on June 27, 2026, the docling-project/docling.rs repository has 111 stars and 32 forks, with 1 open issues. It has more stars than 68% of the servers in the directory. It received changes this month. Version published in the registry: 2.51.1 (October 24, 2026).

Stars measure attention, not quality: a recent, heavily promoted project can collect them fast, while a useful but niche server will have few.

MarkitdownMarkitdown : 191.9K191.9KPuterPuter : 43.9K43.9KFilestashFilestash : 14.8K14.8KRevoGrid DataGrid MCPRevoGrid DataGrid MCP : 3.5K3.5KDocling MCPDocling MCP : 777777MCP filesystem serverMCP filesystem server : 692692Haiku.ragHaiku.rag : 636636MuMu : 436436Docling.rsDocling.rs : 111111
GitHub stars of the most followed servers in the category (log scale); Docling.rs in orange. Checked October 25, 2026.

Verdict

Docling.rs is a reasonable choice; check the points below before connecting it.

Strengths

  • Active project: recent commit
  • Listed in the official MCP registry
  • Permissive licence (MIT)

Avoid if…

  • You cannot isolate the agent (sandbox, container)

Frequently asked questions

How do I install Docling.rs?

Docling.rs is distributed as PyPI package (Python, started with uvx or pip) and Docker (OCI) image. Add it to your client's MCP configuration (Claude Desktop, Cursor, VS Code…) following the README of docling-project/docling.rs.

Is Docling.rs free?

The code is published under the MIT licence and can be used free of charge.

Is Docling.rs safe?

Points to watch: system access. Give it minimum rights and approve sensitive actions.

Is it an official server?

Nothing says so: it is a project published by docling-project on GitHub. Check who maintains it before giving it access.

What are the alternatives to Docling.rs?

In the same category: Markitdown, Puter, Filestash, and RevoGrid DataGrid MCP. Markitdown and Puter score higher on our grid.

Related articles

Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score