How to Use the Hyperbrowser (Web Infra for AI) MCP in AutoGen

Q: How do AutoGen agents share a single Hyperbrowser (Web Infra for AI) session?

The manager agent calls createsession and shares the resulting session ID in the group chat. Any agent with access to the MCP toolset can then run runscript or pagescreenshot against that specific session.

Q: Can an AutoGen critic agent verify scraping results using Hyperbrowser (Web Infra for AI)?

Yes, a critic agent can call pagescreenshot to visually inspect the current state of the browser, or use pagecontent to verify that the raw HTML contains the required target elements.

Coordinate multi-agent browser automation and consensus-driven scraping in AutoGen using Hyperbrowser.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hyperbrowser (Web Infra for AI) MCP to AutoGen

Create your Vinkius account to connect Hyperbrowser (Web Infra for AI) 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 Hyperbrowser (Web Infra for AI) with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent browser session coordination

The `create_session` tool allows your AutoGen coordinator to spin up a dedicated browser instance that multiple specialized agents can access. For example, a research agent can navigate the page while a security agent calls `get_session` to monitor proxy health and session duration. Because AutoGen relies on agent conversations, one agent can propose a JS interaction, while another executes it via `run_script` and returns the output to the group. This collaborative approach ensures complex automation scripts are verified by multiple perspectives before running.

Consensus-driven extraction via AutoGen and MCP Server

The `extract_data` tool lets an AutoGen extraction agent pull structured JSON from a dynamic page and present it to a critic agent. The critic agent can verify the schema accuracy and, if needed, instruct a browser agent to fetch more raw HTML using `page_content`. This loop ensures the extracted data is highly accurate before it gets written to your database. By delegating the heavy rendering to the MCP Server, your agents focus entirely on analyzing the extracted data.

Asynchronous task delegation in agent swarms

The `start_scrape` tool enables an AutoGen manager agent to dispatch long-running scraping tasks to the background without blocking the conversation flow. Other agents can continue discussing strategy or processing existing data while a designated checker agent polls `get_scrape_job`. Once the checker agent receives the completed payload, it injects it back into the AutoGen group chat. If a job fails, the manager agent can run `list_sessions` and `stop_session` to clean up resources and spin up a fresh attempt.

Setup guide

Set up Hyperbrowser (Web Infra for AI) 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 Hyperbrowser (Web Infra for AI) 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="Hyperbrowser (Web Infra for AI)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Hyperbrowser (Web Infra for AI) 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="Hyperbrowser (Web Infra for AI)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Hyperbrowser (Web Infra for AI) 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 Hyperbrowser. 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 Hyperbrowser (Web Infra for AI) 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 Hyperbrowser (Web Infra for AI) MCP in AutoGen

The manager agent calls `create_session` and shares the resulting session ID in the group chat. Any agent with access to the MCP toolset can then run `run_script` or `page_screenshot` against that specific session.

Yes, a critic agent can call `page_screenshot` to visually inspect the current state of the browser, or use `page_content` to verify that the raw HTML contains the required target elements.

You can configure custom stealth settings and proxy rules during the `create_session` call. This keeps your multi-agent conversations running smoothly without triggering anti-bot blocks on target sites.

Designate a housekeeper agent in your AutoGen group to monitor session health. This agent can list active sessions with `list_sessions` on the MCP Server and call `stop_session` on any instance that has exceeded its idle timeout.

Yes, all session state, cookies, and scraped web data are isolated inside secure, ephemeral containers. The data is never persisted on disk and is completely purged from the infrastructure immediately upon session termination.

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