How to Use the Browserhub MCP in AutoGen

Q: Can AutoGen use Browserhub to scrape multiple sites?

Yes, agents can iterate through a list of URLs by calling runscraper sequentially. They coordinate the sequence to ensure they don't hit limits.

Q: Do AutoGen agents share my Browserhub balance?

Only if you authorize the tool. You can restrict the getaccountbalance tool to a specific agent, ensuring only the budget-manager agent sees your credit status.

Let your AutoGen agents debate and execute web scraping tasks with Browserhub.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browserhub MCP to AutoGen

Create your Vinkius account to connect Browserhub 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 Browserhub with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate scraping tasks with Browserhub and AutoGen

Create a security agent and a scraping agent that negotiate the best way to use `direct_scrape`. They check for risks before finalizing the job execution. This consensus model prevents accidental scraping of unauthorized sites. The agents deliberate until they agree on the specific parameters for the tool call.

Automated job management in AutoGen

Assign an agent to monitor `list_scraping_jobs` and report back to the team. If a job stalls, the agents discuss whether to restart or skip it. It removes the need for manual oversight. Your agents handle the entire lifecycle, from starting a scraper to reviewing the final output.

Validate scraping results in AutoGen

Use one agent to execute `run_scraper` and another to verify the results. They confirm the data quality before moving to the next task in your workflow. This check-and-balance system ensures you only get clean data. If the output is low quality, the agents negotiate a new attempt using a different blueprint.

Setup guide

Set up Browserhub 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 Browserhub 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="Browserhub_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

They use the MCP adapter to share the tool definitions. Agents then propose tool calls in the conversation, which other agents review and approve.

Yes, agents can iterate through a list of URLs by calling `run_scraper` sequentially. They coordinate the sequence to ensure they don't hit limits.

Every request requires a unique Vinkius token. Your scraped content is only shared within the agent conversation and is never cached by the server itself.

Only if you authorize the tool. You can restrict the `get_account_balance` tool to a specific agent, ensuring only the budget-manager agent sees your credit status.

The agents continue their conversation until they reach a consensus. You can watch the full dialogue to see exactly why they chose a specific scraper or URL.

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