MCP.so
ログイン

MCP Docling Server

@zanetworker

MCP Docling Server について

An MCP server to help you "play with your documents" via Docling 🐥

基本情報

カテゴリ

その他

ライセンス

MIT

ランタイム

python

トランスポート

stdio

公開者

zanetworker

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "mcp-docling": {
      "command": "uv",
      "args": [
        "run",
        "mcp-server-lls"
      ]
    }
  }
}

ツール

13

URL or local file path to the document (required)

Whether to enable OCR for scanned documents (optional, default: false)

List of language codes for OCR, e.g. ["en", "fr"] (optional)

URL or local file path to the document (required)

Whether to enable OCR for scanned documents (optional, default: false)

List of language codes for OCR (optional)

URL or local file path to the document (required)

List of URLs or file paths to documents (required)

Whether to enable OCR for scanned documents (optional, default: false)

List of language codes for OCR (optional)

URL or local file path to the document (required)

Number of expected Q&As (optional, default: 5)

This tool requires IBM Watson X credentials to be set as environment variables:

概要

What is MCP Docling Server?

An MCP server that provides document processing capabilities using the Docling library. It exposes tools to convert, extract tables, batch process, and generate Q&A from documents. Designed for developers building LLM‑powered document workflows.

How to use MCP Docling Server?

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.

Key features of MCP Docling Server

  • 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

Use cases of MCP Docling Server

  • Convert research papers to Markdown for LLM ingestion
  • Extract tables from financial or scientific reports
  • Batch process a folder of PDFs at once
  • Create Q&A datasets from documentation for training
  • Integrate document parsing into LLM agent toolchains

FAQ from MCP Docling Server

What transport protocols are supported?

Both stdio (default) and SSE transport are supported; you can set a custom port

コメント

「その他」の他のコンテンツ