CuratedMCP
Gemini CLI
PyPI

How to install Docling MCP in Gemini CLI

Convert PDFs and other documents to structured formats via Docling, for AI applications.

Indexed, not yet reviewed

We found Docling MCP in the official MCP registry. Our automated check passed on Nov 1, 2026 (it confirms the server is published and reachable), but no one at CuratedMCP has reviewed its code, permissions or credentials handling. Check what it can access before you give it keys. Scan your machine free to see every MCP server you have installed.

Steps

  1. 1Install uv (for uvx): https://docs.astral.sh/uv/
  2. 2Open ~/.gemini/settings.json (or .gemini/settings.json in your project)
  3. 3Add the entry below. If the file already has "mcpServers", add just the inner entry
  4. 4Restart Gemini CLI and run /mcp to confirm

Configuration

~/.gemini/settings.json
{
  "mcpServers": {
    "docling": {
      "command": "uvx",
      "args": [
        "docling-mcp"
      ]
    }
  }
}
Environment variableRequiredWhat it is
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 backend. Default: false.
DOCLING_MCP_PICTURE_DESCRIPTION_PRESETNoPreset 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_MODENoControls 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_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.

Install in other clients

About Docling MCP: repo, license and check results →

Maintain Docling MCP?

Claim this page to get a full CuratedMCP listing: edit your description, see listing analytics, and add our README badge. Listing is free, and a person checks every submission before it goes live. We'll pre-fill the form from the registry.

    How to install Docling MCP server in Gemini CLI | CuratedMCP