docs: Add instructions for using Docling with MCP to README (#2219)

* docs: Add instructions for using Docling with MCP to README

* DCO Remediation Commit for Roy Derks <[email protected]>

Signed-off-by: Roy Derks <[email protected]>

* DCO Remediation Commit for Roy Derks <[email protected]>

I, Roy Derks <[email protected]>, hereby add my Signed-off-by to this commit: 4b9ba1d

Signed-off-by: Roy Derks <[email protected]>

* docs: reorganize documentation on MCP server

Signed-off-by: Cesar Berrospi Ramis <[email protected]>

* docs: align README with documentation index page

Signed-off-by: Cesar Berrospi Ramis <[email protected]>

---------

Signed-off-by: Roy Derks <[email protected]>
Signed-off-by: Cesar Berrospi Ramis <[email protected]>
Co-authored-by: Roy Derks <[email protected]>
Co-authored-by: Cesar Berrospi Ramis <[email protected]>

Author: 3 people

README.md

@@ -38,16 +38,20 @@ Docling simplifies document processing, parsing diverse formats — including ad
 * 🔍 Extensive OCR support for scanned PDFs and images
 * 👓 Support of several Visual Language Models ([SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview))
 * 🎙️ Audio support with Automatic Speech Recognition (ASR) models
+* 🔌 Connect to any agent using the [MCP server](https://docling-project.github.io/docling/usage/mcp/)
 * 💻 Simple and convenient CLI
 
 ### What's new
 * 📤 Structured [information extraction][extraction] \[🧪 beta\]
+* 📑 New layout model (**Heron**) by default, for faster PDF parsing
+* 🔌 [MCP server](https://docling-project.github.io/docling/usage/mcp/) for agentic applications
 
 ### Coming soon
 
 * 📝 Metadata extraction, including title, authors, references & language
 * 📝 Chart understanding (Barchart, Piechart, LinePlot, etc)
 * 📝 Complex chemistry understanding (Molecular structures)
+* 📝 Parsing of Web Video Text Tracks (WebVTT) files
 
 ## Installation
 
@@ -73,7 +77,7 @@ result = converter.convert(source)
 print(result.document.export_to_markdown())  # output: "## Docling Technical Report[...]"
 ```
 
-More [advanced usage options](https://docling-project.github.io/docling/usage/) are available in
+More [advanced usage options](https://docling-project.github.io/docling/usage/advanced_options/) are available in
 the docs.
 
 ## CLI

docs/index.md

@@ -30,13 +30,20 @@ Docling simplifies document processing, parsing diverse formats — including ad
 * 🔍 Extensive OCR support for scanned PDFs and images
 * 👓 Support of several Visual Language Models ([SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview))
 * 🎙️  Support for Audio with Automatic Speech Recognition (ASR) models
+* 🔌 Connect to any agent using the [Docling MCP](https://docling-project.github.io/docling/usage/mcp/) server
 * 💻 Simple and convenient CLI
 
+### What's new
+* 📤 Structured [information extraction][extraction] \[🧪 beta\]
+* 📑 New layout model (**Heron**) by default, for faster PDF parsing
+* 🔌 [MCP server](https://docling-project.github.io/docling/usage/mcp/) for agentic applications
+
 ### Coming soon
 
 * 📝 Metadata extraction, including title, authors, references & language
 * 📝 Chart understanding (Barchart, Piechart, LinePlot, etc)
 * 📝 Complex chemistry understanding (Molecular structures)
+* 📝 Parsing of Web Video Text Tracks (WebVTT) files
 
 ## Get started
 

docs/usage/mcp.md

@@ -0,0 +1,31 @@
+New AI trends focus on Agentic AI, an artificial intelligence system that can accomplish a specific goal with limited supervision.
+Agents can act autonomously to understand, plan, and execute a specific task.
+
+To address the integration problem, the [Model Context Protocol](https://modelcontextprotocol.io) (MCP) emerges as a popular standard for connecting AI applications to external tools.
+
+## Docling MCP
+
+Docling supports the development of AI agents by providing an MCP Server. It allows you to experiment with document processing in different MCP Clients. Adding [Docling MCP](https://github.com/docling-project/docling-mcp) in your favorite client is usually as simple as adding the following entry in the configuration file:
+
+```json
+{
+  "mcpServers": {
+    "docling": {
+      "command": "uvx",
+      "args": [
+        "--from=docling-mcp",
+        "docling-mcp-server"
+      ]
+    }
+  }
+}
+```
+
+When using [Claude on your desktop](https://claude.ai/download), just edit the config file `claude_desktop_config.json` with the snippet above or the example provided [here](https://github.com/docling-project/docling-mcp/blob/main/docs/integrations/claude_desktop_config.json).
+
+In **[LM Studio](https://lmstudio.ai/)**, edit the `mcp.json` file with the appropriate section or simply clik on the button below for a direct install.
+
+[![Add MCP Server docling to LM Studio](https://files.lmstudio.ai/deeplink/mcp-install-light.svg)](https://lmstudio.ai/install-mcp?name=docling&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyItLWZyb209ZG9jbGluZy1tY3AiLCJkb2NsaW5nLW1jcC1zZXJ2ZXIiXX0%3D)
+
+
+Docling MCP also provides tools specific for some applications and frameworks. See the [Docling MCP](https://github.com/docling-project/docling-mcp) Server repository for more details. You will find examples of building agents powered by Docling capabilities and leveraging frameworks like [LlamaIndex](https://www.llamaindex.ai/), [Llama Stack](https://github.com/llamastack/llama-stack), [Pydantic AI](https://ai.pydantic.dev/), or [smolagents](https://github.com/huggingface/smolagents).

mkdocs.yml

@@ -65,6 +65,7 @@ nav:
       - Supported formats: usage/supported_formats.md
       - Enrichment features: usage/enrichments.md
       - Vision models: usage/vision_models.md
+      - MCP server: usage/mcp.md
     - FAQ:
       - FAQ: faq/index.md
   - Concepts: