How to Use the Crawlbase MCP in AutoGen

Q: How do I configure the Crawlbase tools in AutoGen?

Install autogen-extmcp. Use mcpservertools with StreamableHttpServerParams pointing to your Vinkius endpoint. Pass the resulting tool list to your AssistantAgent constructor.

Give your AutoGen debating agents the ability to scrape the web and verify facts using the Crawlbase MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Crawlbase MCP to AutoGen

Create your Vinkius account to connect Crawlbase 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 Crawlbase with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fact-checking through the MCP Server

Your debating agents need external proof to settle arguments. Connecting this MCP Server gives them a direct line to live web data. A researcher agent can run `scrape_html` to pull primary sources while a critic agent reviews the output. Some sources sit behind heavy anti-bot protection. When an agent calls `scrape_js_rendered`, the server handles the browser execution and proxy rotation. The conversation never stalls because of a Cloudflare block.

Social media consensus building

Analyzing public sentiment requires multiple perspectives. One agent can execute `scrape_twitter` to fetch mapped limits of user posts. Another agent can parallelize `scrape_facebook` to cross-reference active social pages. Professional background checks demand accuracy. Triggering `scrape_linkedin` retrieves structural matching for specific profiles. Your agents debate the merits of a candidate based on verified job histories.

E-commerce and search negotiations

Pricing strategies require agents to compare different markets. A buyer agent uses `scrape_amazon` to inspect internal arrays for product costs. A market analyst agent simultaneously runs `scrape_google_serp` to check competitor search rankings. Sometimes visual evidence is the only way to resolve a layout dispute. Firing `get_screenshot_link` dispatches an automated validation check. The agents receive a direct snapshot URL to confirm what the page actually looked like at that exact second.

Setup guide

Set up Crawlbase 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 Crawlbase 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="Crawlbase_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Crawlbase 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="Crawlbase_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Crawlbase 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 Crawlbase. 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 Crawlbase 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 Crawlbase MCP in AutoGen

Install `autogen-ext[mcp]`. Use `mcp_server_tools` with `StreamableHttpServerParams` pointing to your Vinkius endpoint. Pass the resulting tool list to your `AssistantAgent` constructor.

Yes. You can equip different agents with specific scraping tools based on their roles. A researcher might have the HTML scraper while a social media analyst gets the Twitter tool.

The server handles all proxy rotation and CAPTCHA solving server-side. Your agents simply request a URL and wait for the response. They don't need complex logic to handle retries or browser emulation.

Agents can use the JSON formatting tool to perform structural extraction. This returns clean properties instead of bloated DOM strings. It saves significant context window space during multi-agent debates.

Agent-selected URLs and the resulting HTML payloads remain strictly within the Vinkius boundary. The environment relies on stateless, single-use sandboxes. All request data vanishes the moment the connection closes.

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