Docling MCP Server

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

claude mcp add docling-mcp -- uvx docling-mcp

{
  "mcpServers": {
    "docling-mcp": {
      "command": "uvx",
      "args": [
        "docling-mcp"
      ]
    }
  }
}

[mcp_servers.docling-mcp]
command = "uvx"
args = ["docling-mcp"]

{
  "mcpServers": {
    "docling-mcp": {
      "command": "uvx",
      "args": [
        "docling-mcp"
      ]
    }
  }
}

{
  "servers": {
    "docling-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "docling-mcp"
      ]
    }
  }
}

Optional settings from the registry entry, left out of the block above: DOCLING_MCP_CONVERSION_MODE (Conversion mode: 'remote' (default) or 'local' (requires docling-mcp[local] extra)), DOCLING_MCP_SERVICE_URL (Base URL of the Docling Serve instance. Required when conversion mode is remote), DOCLING_MCP_SERVICE_API_KEY (API key for authenticating with Docling Serve), DOCLING_MCP_SERVICE_TIMEOUT (Request timeout in seconds for the remote Docling Serve API. Default: 300.0), DOCLING_MCP_SERVICE_MAX_RETRIES (Maximum number of retry attempts for remote API requests. Default: 3), DOCLING_MCP_FALLBACK_TO_LOCAL (Set to 'true' to fall back to local conversion when Docling Serve is unreachable), DOCLING_MCP_KEEP_IMAGES (Set to 'true' to retain page images in converted documents. Default: false), DOCLING_MCP_IMAGES_SCALE (Image scale factor (e.g. 1.0, 2.0). Increase to avoid tensor batching errors. Default: 1.0), DOCLING_MCP_DO_OCR (Set to 'false' to disable the OCR pipeline. Default: true), DOCLING_MCP_DO_TABLE_STRUCTURE (Set to 'false' to disable table structure detection. Default: true), DOCLING_MCP_DO_PICTURE_DESCRIPTION (Set 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 backend. Default: false), DOCLING_MCP_PICTURE_DESCRIPTION_PRESET (Preset ID for the picture-description VLM (e.g. 'smolvlm', 'granite_vision'). When unset the backend default is used. Only applies when DOCLING_MCP_DO_PICTURE_DESCRIPTION=true), DOCLING_MCP_IMAGE_EXPORT_MODE (Controls how images are rendered when exporting to Markdown. Accepted values: 'placeholder' (default, emits <!-- image -->), 'embedded' (base64 data-URI), 'referenced' (file path / URL)), DOCLING_MCP_CACHE_MAX_DOCUMENTS (Maximum number of documents to keep in the in-memory cache. Oldest (least-recently-used) documents are evicted when the limit is reached. Default: 10).