# docling.rs (MCP server)

> docling.rs is an MCP server that adds search and knowledge tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Documents to Markdown for agents: PDF layout, tables and OCR, Office, HTML, scans. It has 112 GitHub stars, is released under the MIT license and runs locally with uvx docling-rs-mcp.

docling.rs converts documents — PDF, Office, HTML, scans, audio — into Markdown, docling JSON and the other shapes an LLM or a RAG pipeline can read. It is a Rust port of IBM's docling: the same output, byte-for-byte, from one static binary. No Python, no PyTorch.

## Key facts

| Fact | Value |
|---|---|
| Repository | https://github.com/docling-project/docling.rs |
| GitHub stars | 112 |
| License | MIT |
| Language | Rust |
| Transport | stdio |
| Packages | pypi: docling-rs-mcp; docker: ghcr.io/docling-project/docling-rs:2.51.3 |
| Remote URL | none |
| Needs API key | no |
| Official | no |
| Works with | Claude Desktop, Claude Code, Cursor, VS Code |
| Category | AI & search |
| Latest release | v2.51.3 (Oct 24, 2026) |
| Last commit | Oct 26, 2026 |
| MCP registry name | io.github.docling-project/docling-rs |

## Install

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "docling-rs": {
      "command": "uvx",
      "args": [
        "docling-rs-mcp"
      ],
      "env": {
        "DOCLING_RS_CACHE_DIR": "your-value",
        "DOCLING_RS_OCR_LANG": "your-value"
      }
    }
  }
}
```

Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.

### Claude Code

```sh
claude mcp add --env DOCLING_RS_CACHE_DIR=your-value --env DOCLING_RS_OCR_LANG=your-value --transport stdio docling-rs -- uvx docling-rs-mcp
```

### Cursor (.cursor/mcp.json)

```json
{
  "mcpServers": {
    "docling-rs": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "docling-rs-mcp"
      ],
      "env": {
        "DOCLING_RS_CACHE_DIR": "your-value",
        "DOCLING_RS_OCR_LANG": "your-value"
      }
    }
  }
}
```

Project file; use ~/.cursor/mcp.json to enable it in every project.

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "docling-rs": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "docling-rs-mcp"
      ],
      "env": {
        "DOCLING_RS_CACHE_DIR": "your-value",
        "DOCLING_RS_OCR_LANG": "your-value"
      }
    }
  }
}
```

Config formats checked against the official docs on 2026-10-07.

## Environment variables

- `DOCLING_RS_CACHE_DIR`: Where docling-rs-mcp --download-models puts the PDF/image models and the server finds them (default ~/.cache/docling.rs).
- `DOCLING_RS_OCR_LANG`: OCR language for scans: en (default), ch, or a BCP-47 tag.

## Similar MCP servers

- [Agent Search MCP](https://appsgit.com/mcp-servers/agent-search-mcp): Free-first Chinese and English web search MCP using zero-key sources and inspectable evidence. (112 stars, Apache-2.0)
- [DocsMint](https://appsgit.com/mcp-servers/docsmint): Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools. (109 stars, Apache-2.0, needs API key)
- [Vectorize MCP Server](https://appsgit.com/mcp-servers/vectorize-mcp-server): A Model Context Protocol (MCP) server implementation that integrates with Vectorize for advanced Vector retrieval and text extraction. (115 stars, MIT, needs API key)
- [loci](https://appsgit.com/mcp-servers/loci): Cross-session memory and hybrid RAG over your notes and docs. (101 stars, MIT)
- [Hexis](https://appsgit.com/mcp-servers/hexis): Git-backed platform for skills, tools, and context for AI agents. (120 stars, Apache-2.0)
- [Knolo](https://appsgit.com/mcp-servers/knolo): Verified, local-first retrieval over pinned Knolo Knowledge Images. (51 stars, Apache-2.0, official)

---

Canonical page: https://appsgit.com/mcp-servers/docling-rs
Source: appsgit (https://appsgit.com), the app store for github. Data from the GitHub API, refreshed daily.
Machine access: JSON API https://appsgit.com/api/v1/apps (OpenAPI: https://appsgit.com/openapi.json), MCP server https://mcp.appsgit.com/mcp, full index https://appsgit.com/llms-full.txt.