Skip to content
appsgit

Docling MCP

Docling MCP is an MCP server that adds tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Convert PDFs and other documents to structured formats via Docling, for AI applications. It has 768 GitHub stars, is released under the MIT license and runs locally with uvx docling-mcp.

github.com/docling-project/docling-mcp (opens in a new tab)

  • Needs API key
  • Other
  • MIT
  • Actively maintained

Install Docling MCP

Generated from the server's MCP registry entry. Replace your-value with your own values.

Claude Desktop

claude_desktop_config.json
{
  "mcpServers": {
    "docling-mcp": {
      "command": "uvx",
      "args": [
        "docling-mcp"
      ],
      "env": {
        "DOCLING_MCP_SERVICE_API_KEY": "your-value"
      }
    }
  }
}

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

Claude Code

claude mcp add --env DOCLING_MCP_SERVICE_API_KEY=your-value --transport stdio docling-mcp -- uvx docling-mcp

Cursor

.cursor/mcp.json
{
  "mcpServers": {
    "docling-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "docling-mcp"
      ],
      "env": {
        "DOCLING_MCP_SERVICE_API_KEY": "your-value"
      }
    }
  }
}

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

VS Code

.vscode/mcp.json
{
  "inputs": [
    {
      "type": "promptString",
      "id": "docling_mcp_service_api_key",
      "description": "DOCLING_MCP_SERVICE_API_KEY",
      "password": true
    }
  ],
  "servers": {
    "docling-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "docling-mcp"
      ],
      "env": {
        "DOCLING_MCP_SERVICE_API_KEY": "${input:docling_mcp_service_api_key}"
      }
    }
  }
}

Config formats checked against the official docs on Oct 7, 2026: modelcontextprotocol.io (opens in a new tab), code.claude.com (opens in a new tab), cursor.com (opens in a new tab), code.visualstudio.com (opens in a new tab).

Environment variables

Variables the server reads at startup.

NameRequiredDescription
DOCLING_MCP_CONVERSION_MODENoConversion mode: 'remote' (default) or 'local' (requires docling-mcp[local] extra).
DOCLING_MCP_SERVICE_URLNoBase URL of the Docling Serve instance. Required when conversion mode is remote.
DOCLING_MCP_SERVICE_API_KEYsecretNoAPI key for authenticating with Docling Serve.
DOCLING_MCP_SERVICE_TIMEOUTNoRequest timeout in seconds for the remote Docling Serve API. Default: 300.0.
DOCLING_MCP_SERVICE_MAX_RETRIESNoMaximum number of retry attempts for remote API requests. Default: 3.
DOCLING_MCP_FALLBACK_TO_LOCALNoSet to 'true' to fall back to local conversion when Docling Serve is unreachable.
DOCLING_MCP_KEEP_IMAGESNoSet to 'true' to retain page images in converted documents. Default: false.
DOCLING_MCP_IMAGES_SCALENoImage scale factor (e.g. 1.0, 2.0). Increase to avoid tensor batching errors. Default: 1.0.
DOCLING_MCP_DO_OCRNoSet to 'false' to disable the OCR pipeline. Default: true.
DOCLING_MCP_DO_TABLE_STRUCTURENoSet to 'false' to disable table structure detection. Default: true.
DOCLING_MCP_DO_PICTURE_DESCRIPTIONNoSet to 'true' to run a vision-language model to generate textual descriptions for figures and pictures. Requires a VLM to be available on the conversion…
DOCLING_MCP_PICTURE_DESCRIPTION_PRESETNoPreset ID for the picture-description VLM (e.g. 'smolvlm', 'granitevision'). When unset the backend default is used. Only applies when…
DOCLING_MCP_IMAGE_EXPORT_MODENoControls how images are rendered when exporting to Markdown. Accepted values: 'placeholder' (default, emits ), 'embedded' (base64 data-URI), 'referenced'…
DOCLING_MCP_CACHE_MAX_DOCUMENTSNoMaximum number of documents to keep in the in-memory cache. Oldest (least-recently-used) documents are evicted when the limit is reached. Default: 10.

About Docling MCP

A document processing service using the Docling-MCP library and MCP (Model Context Protocol) for tool integration. 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.

FAQ

Docling MCP FAQ

Still curious? Email info@appsgit.com.

What is Docling MCP?

Docling MCP is an MCP server that adds tools to AI assistants such as Claude Desktop, Claude Code and Cursor. Convert PDFs and other documents to structured formats via Docling, for AI applications. It has 768 GitHub stars, is released under the MIT license and runs locally with uvx docling-mcp. The source code is at github.com/docling-project/docling-mcp.

How do I install the Docling MCP MCP server?

Add the command uvx docling-mcp to your MCP client: put it in claude_desktop_config.json for Claude Desktop, run claude mcp add for Claude Code, or add it to .cursor/mcp.json (Cursor) or .vscode/mcp.json (VS Code). The snippets on this page are ready to paste.

Is Docling MCP free?

The server is open source under the MIT license, so running it is free. It needs credentials (DOCLING_MCP_SERVICE_API_KEY) for the service it connects to, which may require a paid account.

Is Docling MCP actively maintained?

The most recent commit was on Oct 6, 2026. The latest release is v3.3.0, published Oct 6, 2026. appsgit only lists MCP servers with a commit in the last six months and re-checks every server daily.