# Agent Development Kit (ADK) (/developer-guides/llm-sdks-and-frameworks/google-adk)

<!-- agent-signals: reading_time_min: 4 · est_tokens: 1911 · updated: 2026-07-30 -->
Related: [OpenAI](/developer-guides/llm-sdks-and-frameworks/openai.md), [Anthropic](/developer-guides/llm-sdks-and-frameworks/anthropic.md), [Gemini](/developer-guides/llm-sdks-and-frameworks/gemini.md), [Vercel AI SDK](/developer-guides/llm-sdks-and-frameworks/vercel-ai-sdk.md), [LangChain](/developer-guides/llm-sdks-and-frameworks/langchain.md), [LangGraph](/developer-guides/llm-sdks-and-frameworks/langgraph.md)

Integrate Firecrawl with Google's Agent Development Kit (ADK) to build powerful AI agents with web scraping capabilities through the Model Context Protocol (MCP).

## Overview [#overview]

Firecrawl provides an MCP server that seamlessly integrates with Google's ADK, enabling your agents to efficiently scrape, crawl, and extract structured data from any website. The integration supports both cloud-based and self-hosted Firecrawl instances with streamable HTTP for optimal performance.

## Features [#features]

* Efficient web scraping, crawling, and content discovery from any website
* Advanced search capabilities and intelligent content extraction
* Deep research
* Flexible deployment (cloud-based or self-hosted)
* Optimized for modern web environments with streamable HTTP support

## Prerequisites [#prerequisites]

* Obtain an API key for Firecrawl from [firecrawl.dev](https://firecrawl.dev)
* Install Google ADK

## Setup [#setup]

<CodeGroup>
  <CodeBlockTabs defaultValue="Remote MCP Server" groupId="local-mcp-server+remote-mcp-server">
    <CodeBlockTabsList>
      <CodeBlockTabsTrigger value="Remote MCP Server">
        Remote MCP Server
      </CodeBlockTabsTrigger>

      <CodeBlockTabsTrigger value="Local MCP Server">
        Local MCP Server
      </CodeBlockTabsTrigger>
    </CodeBlockTabsList>

    <CodeBlockTab value="Remote MCP Server">
      ```python  
      from google.adk.agents.llm_agent import Agent
      from google.adk.tools.mcp_tool.mcp_session_manager import StreamableHTTPServerParams
      from google.adk.tools.mcp_tool.mcp_toolset import MCPToolset

      FIRECRAWL_API_KEY = "YOUR-API-KEY"

      root_agent = Agent(
          model="gemini-2.5-pro",
          name="firecrawl_agent",
          description='A helpful assistant for scraping websites with Firecrawl',
          instruction='Help the user search for website content',
          tools=[
              MCPToolset(
                  connection_params=StreamableHTTPServerParams(
                      url="https://mcp.firecrawl.dev/v2/mcp",
                      headers={"Authorization": f"Bearer {FIRECRAWL_API_KEY}"},
                  ),
              )
          ],
      )
      ```
    </CodeBlockTab>

    <CodeBlockTab value="Local MCP Server">
      ```python  
      from google.adk.agents.llm_agent import Agent
      from google.adk.tools.mcp_tool.mcp_session_manager import StdioConnectionParams
      from google.adk.tools.mcp_tool.mcp_toolset import MCPToolset
      from mcp import StdioServerParameters

      root_agent = Agent(
          model='gemini-2.5-pro',
          name='firecrawl_agent',
          description='A helpful assistant for scraping websites with Firecrawl',
          instruction='Help the user search for website content',
          tools=[
              MCPToolset(
                  connection_params=StdioConnectionParams(
                      server_params = StdioServerParameters(
                          command='npx',
                          args=[
                              "-y",
                              "firecrawl-mcp",
                          ],
                          env={
                              "FIRECRAWL_API_KEY": "YOUR-API-KEY",
                          }
                      ),
                      timeout=30,
                  ),
              )
          ],
      )
      ```
    </CodeBlockTab>
  </CodeBlockTabs>
</CodeGroup>

## Available Tools [#available-tools]

| Tool               | Name                           | Description                                                          |
| ------------------ | ------------------------------ | -------------------------------------------------------------------- |
| Scrape Tool        | `firecrawl_scrape`             | Scrape content from a single URL with advanced options               |
| Map Tool           | `firecrawl_map`                | Map a website to discover all indexed URLs on the site               |
| Search Tool        | `firecrawl_search`             | Search the web and optionally extract content from search results    |
| Crawl Tool         | `firecrawl_crawl`              | Start an asynchronous crawl with advanced options                    |
| Check Crawl Status | `firecrawl_check_crawl_status` | Check the status of a crawl job                                      |
| Extract Tool       | `firecrawl_extract`            | Extract structured information from web pages using LLM capabilities |

## Configuration [#configuration]

### Required Configuration [#required-configuration]

**FIRECRAWL\_API\_KEY**: Your Firecrawl API key

* Required when using cloud API (default)
* Optional when using self-hosted instance with FIRECRAWL\_API\_URL

### Optional Configuration [#optional-configuration]

**Firecrawl API URL (for self-hosted instances)**:

* `FIRECRAWL_API_URL`: Custom API endpoint
* Example: `https://firecrawl.your-domain.com`
* If not provided, the cloud API will be used

## Example: Web Research Agent [#example-web-research-agent]

```python
from google.adk.agents.llm_agent import Agent
from google.adk.tools.mcp_tool.mcp_session_manager import StreamableHTTPServerParams
from google.adk.tools.mcp_tool.mcp_toolset import MCPToolset

FIRECRAWL_API_KEY = "YOUR-API-KEY"

# Create a research agent
research_agent = Agent(
    model="gemini-2.5-pro",
    name="research_agent",
    description='An AI agent that researches topics by scraping and analyzing web content',
    instruction='''You are a research assistant. When given a topic or question:
    1. Use the search tool to find relevant websites
    2. Scrape the most relevant pages for detailed information
    3. Extract structured data when needed
    4. Provide comprehensive, well-sourced answers''',
    tools=[
        MCPToolset(
            connection_params=StreamableHTTPServerParams(
                url="https://mcp.firecrawl.dev/v2/mcp",
                headers={"Authorization": f"Bearer {FIRECRAWL_API_KEY}"},
            ),
        )
    ],
)

# Use the agent
response = research_agent.run("What are the latest features in Python 3.13?")
print(response)
```

## Best Practices [#best-practices]

1. **Use the right tool for the job**:
   * `firecrawl_search` when you need to find relevant pages first
   * `firecrawl_scrape` for single pages
   * `firecrawl_crawl` for discovering and scraping entire sites
   * repeated `firecrawl_scrape` calls when you already have a short list of known URLs

2. **Monitor your usage**: Use your Firecrawl dashboard and API responses to track credit usage.

3. **Handle errors gracefully**: Surface MCP/API errors to the user and retry only when your agent workflow can do so safely.

4. **Optimize performance**: Use `firecrawl_map` before scraping when the agent needs to discover relevant URLs.

***

## Related Resources [#related-resources]

<CardGroup cols="2">
  <Card title="Comprehensive Guide to Building AI Agents Using Google Agent Development Kit (ADK) and Firecrawl" href="https://www.firecrawl.dev/blog/google-adk-multi-agent-tutorial">
    Learn how to build powerful multi-agent AI systems using Google's ADK framework with Firecrawl for web scraping capabilities.
  </Card>

  <Card title="MCP Server Documentation" href="https://docs.firecrawl.dev/mcp-server">
    Learn more about Firecrawl's Model Context Protocol (MCP) server integration and capabilities.
  </Card>

  <Card title="Google ADK Official Documentation" href="https://google.github.io/adk-docs/">
    Explore the official Google Agent Development Kit documentation for comprehensive guides and API references.
  </Card>
</CardGroup>