MCP Docling Server
About
An MCP server to help you "play with your documents" via Docling 🐥
Details
- License
- MIT
Explore
- Convert documents to Markdown format
- Extract tables as structured data
- Process multiple documents in batch mode
- Generate Q&A documents (requires IBM Watson X)
- Enable OCR for scanned documents
- Cache processed documents for performance
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
MCP Docling ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install via pip (pip install -e .) and start the server with mcp-server-lls using stdio (default) or SSE transport (--transport sse --port 8000). Tools are then available to any MCP client; the README includes a detailed example with Llama Stack.
source
URL or local file path to the document (required)
enable_ocr
Whether to enable OCR for scanned documents (optional, default: false)
ocr_language
List of language codes for OCR, e.g. ["en", "fr"] (optional)
sources
List of URLs or file paths to documents (required)
no_of_qnas
Number of expected Q&As (optional, default: 5)
WATSONX_PROJECT_ID
Your Watson X project ID
WATSONX_APIKEY
Your IBM Cloud API key
WATSONX_URL
The Watson X API URL (default: https://us-south.ml.cloud.ibm.com)
The server exposes the following tools:
1. convert_document: Convert a document from a URL or local path to markdown format
- source: URL or local file path to the document (required)
- enable_ocr: Whether to enable OCR for scanned documents (optional, default: false)
- ocr_language: List of language codes for OCR, e.g. ["en", "fr"] (optional)
2. convert_document_with_images: Convert a document and extract embedded images
- source: URL or local file path to the document (required)
- enable_ocr: Whether to enable OCR for scanned documents (optional, default: false)
- ocr_language: List of language codes for OCR (optional)
3. extract_tables: Extract tables from a document as structured data
- source: URL or local file path to the document (required)
4. convert_batch: Process multiple documents in batch mode
- sources: List of URLs or file paths to documents (required)
- enable_ocr: Whether to enable OCR for scanned documents (optional, default: false)
- ocr_language: List of language codes for OCR (optional)
5. qna_from_document: Create a Q&A document from a URL or local path to YAML format
- source: URL or local file path to the document (required)
- no_of_qnas: Number of expected Q&As (optional, default: 5)
- Note: This tool requires IBM Watson X credentials to be set as environment variables:
- WATSONX_PROJECT_ID: Your Watson X project ID
- WATSONX_APIKEY: Your IBM Cloud API key
- WATSONX_URL: The Watson X API URL (default: https://us-south.ml.cloud.ibm.com)
6. get_system_info: Get information about system configuration and acceleration status
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp docling server": {
"mcp-docling": {
"command": "uv",
"args": [
"run",
"mcp-server-lls"
]
}
}
}
}McpServers
{
"mcp-docling": {
"command": "uv",
"args": [
"run",
"mcp-server-lls"
]
}
}An MCP server that provides document processing capabilities using the Docling library.
Installation
You can install the package using pip:
pip install -e .
Usage
Start the server using either stdio (default) or SSE transport:
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
