+ 
+
+
+
+
+ ScrapeGraphAI
+AI-powered web scraping, crawling, and data extraction
+
+ AI-powered web scraping, crawling, and data extraction
+
diff --git a/docs/tools/third-party/index.md b/docs/tools/third-party/index.md
index 60969c64e0..44f878693f 100644
--- a/docs/tools/third-party/index.md
+++ b/docs/tools/third-party/index.md
@@ -89,6 +89,16 @@ Check out the following third-party tools that you can use with ADK agents:
+ AI-powered web scraping, crawling, and data extraction
+
diff --git a/docs/tools/third-party/scrapegraphai.md b/docs/tools/third-party/scrapegraphai.md
new file mode 100644
index 0000000000..7f1d821ee6
--- /dev/null
+++ b/docs/tools/third-party/scrapegraphai.md
@@ -0,0 +1,91 @@
+# ScrapeGraphAI
+
+The
+[ScrapeGraphAI MCP Server](https://github.com/ScrapeGraphAI/scrapegraph-mcp)
+connects your ADK agent to [ScrapeGraphAI](https://scrapegraphai.com/). This
+integration enables your agent to extract structured data using natural language
+prompts, handle dynamic content like infinite scrolling, and convert complex
+webpages into clean, usable JSON or Markdown.
+
+## Use cases
+
+- **Scalable Extraction & Crawling**: Extract structured data from single pages
+ or crawl entire websites, leveraging AI to handle dynamic content, infinite
+ scrolling, and large-scale asynchronous operations.
+
+- **Research and Summarization**: Execute AI-powered web searches to research
+ topics, aggregate data from multiple sources, and summarize findings.
+
+- **Agentic Workflows**: Run advanced agentic scraping workflows with
+ customizable steps, complex navigation (like authentication), and structured
+ output schemas.
+
+## Prerequisites
+
+- Create an [API Key](https://dashboard.scrapegraphai.com/register/) in
+ ScrapeGraphAI. Refer to the
+ [documentation](https://docs.scrapegraphai.com/api-reference/introduction) for more information.
+- Install the [ScrapeGraphAI MCP server
+ package](https://pypi.org/project/scrapegraph-mcp/) (requires Python 3.13 or
+ higher):
+
+ ```console
+ pip install scrapegraph-mcp
+ ```
+
+## Use with agent
+
+=== "Local MCP Server"
+
+ ```python
+ from google.adk.agents import Agent
+ from google.adk.tools.mcp_tool.mcp_toolset import MCPToolset
+ from google.adk.tools.mcp_tool.mcp_session_manager import StdioConnectionParams
+ from mcp import StdioServerParameters
+
+ SGAI_API_KEY = "YOUR_SCRAPEGRAPHAI_API_KEY"
+
+ root_agent = Agent(
+ model="gemini-2.5-pro",
+ name="scrapegraph_assistant_agent",
+ instruction="""Help the user with web scraping and data extraction using
+ ScrapeGraph AI. You can convert webpages to markdown, extract
+ structured data using AI, perform web searches, crawl
+ multiple pages, and automate complex scraping workflows.""",
+ tools=[
+ MCPToolset(
+ connection_params=StdioConnectionParams(
+ server_params=StdioServerParameters(
+ # The following CLI command is available
+ # from `pip install scrapegraph-mcp`
+ command="scrapegraph-mcp",
+ env={
+ "SGAI_API_KEY": SGAI_API_KEY,
+ },
+ ),
+ timeout=300,
+ ),
+ # Optional: Filter which tools from the MCP server are exposed
+ # tool_filter=["markdownify", "smartscraper", "searchscraper"]
+ ),
+ ],
+ )
+ ```
+
+## Available tools
+
+Tool