How to Use the Firecrawl MCP in AutoGen

Q: How do I add Firecrawl MCP Server tools to an AutoGen agent?

Install the autogen-ext MCP package and use mcpservertools with StreamableHttpServerParams pointing to your Vinkius URL. Pass the generated tools list directly to your AssistantAgent constructor.

Q: How do AutoGen agents debate the results of a Firecrawl search?

When searchweb returns Markdown content, it enters the group chat history. A critic agent can analyze the text, flag inconsistencies, and ask the researcher agent to run a different query.

Q: Does AutoGen support the async crawl job tracking?

Yes, your agent can call crawlsite, store the job ID in its local state, and use a separate conversation turn to poll for completion while other agents process different tasks.

Equip your AutoGen agents with clean web scraping and crawling tools for collaborative research.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Firecrawl MCP to AutoGen

Create your Vinkius account to connect Firecrawl to AutoGen and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Firecrawl with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative Web Research in AutoGen Teams

In an AutoGen group chat, a researcher agent can use `search_web` to gather raw sources while a writer agent drafts content. The raw Markdown is shared directly in the conversation context for collaborative analysis. This setup allows your agents to debate the quality of the sources. A critic agent can review the scraped content and prompt the researcher to run a more targeted search if details are missing.

Asynchronous Domain Crawling via MCP Server

When auditing a large site, the manager agent calls `crawl_site` to initiate an async crawl. While the crawl runs, other agents can continue analyzing existing data or planning the next steps. The agent checks the crawl job status periodically. Once complete, the resulting Markdown corpus is handed off to specialized analysis agents for structured processing.

Targeted Scraping and Sitemap Mapping

Use `map_site` to let an agent discover the structure of a target domain before committing resources. The agent can then coordinate with a scraper agent to invoke `scrape_page` only on high-value URLs. This collaborative approach avoids redundant work. Your agents negotiate which pages are worth scraping, saving API limits and reducing processing latency.

Setup guide

Set up Firecrawl MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Firecrawl tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Firecrawl_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Firecrawl data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Firecrawl_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Firecrawl data")
    print(result.messages[-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Firecrawl. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Firecrawl now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Firecrawl MCP in AutoGen

Install the autogen-ext MCP package and use mcp_server_tools with StreamableHttpServerParams pointing to your Vinkius URL. Pass the generated tools list directly to your AssistantAgent constructor.

When `search_web` returns Markdown content, it enters the group chat history. A critic agent can analyze the text, flag inconsistencies, and ask the researcher agent to run a different query.

Yes, the Vinkius MCP host handles concurrent requests without bottle-necks. Your coordinator agent can trigger multiple `scrape_page` calls across different worker agents without blocking.

Yes, your agent can call `crawl_site`, store the job ID in its local state, and use a separate conversation turn to poll for completion while other agents process different tasks.

The raw HTML payload, scraped text, and search queries are processed inside secure, isolated V8 instances on our MCP platform. This ensures your scraping targets and parameters are never leaked or stored.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript