How to Use the Browserless MCP in AutoGen

Q: Can one AutoGen agent scrape a page while another analyzes it using Browserless?

Absolutely. A researcher agent uses getpagecontent to fetch the HTML, then passes the text to an analyst agent for extraction and evaluation.

Q: What happens if an AutoGen agent triggers too many Browserless sessions?

The coordinator agent can call getusagestats to monitor consumption. It can then pause tasks or use listactivesessions to clean up old processes.

Let your AutoGen agents debate, scrape, and capture web data using headless Chrome.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Browserless MCP to AutoGen

Create your Vinkius account to connect Browserless 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 Browserless with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent web research and validation

The `get_page_content` tool allows a researcher agent to fetch fully rendered HTML from the web. Once retrieved, a separate critic agent can analyze the raw text to verify claims or spot inconsistencies. If the page requires complex interactions, a specialist agent runs `run_scrape` to execute custom automation scripts. This collaborative loop ensures high-fidelity data extraction without human intervention.

Visual auditing via this Browserless MCP Server

The `take_screenshot` tool captures the exact visual layout of a page for your agent group to inspect. A design agent can review the image while a QA agent checks for rendering bugs. To document the final state, the agents use `generate_pdf` to create a permanent record of the audited page. This output is shared across the conversation thread for immediate validation.

Session and resource management in agent chats

The `list_active_sessions` tool gives your coordinator agent a clear view of all running browser instances. It prevents resource leaks by letting the supervisor agent close idle sessions during long debates. Before spawning new tasks, the group checks `check_system_health` to verify the browser cluster is fully operational. This keeps the multi-agent system from getting stuck in infinite retry loops.

Setup guide

Set up Browserless 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 Browserless 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="Browserless_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

You register the tools using the autogen-ext MCP package. This exposes the entire headless Chrome toolset to any agent in your conversation group.

Absolutely. A researcher agent uses `get_page_content` to fetch the HTML, then passes the text to an analyst agent for extraction and evaluation.

Vinkius manages all authentication tokens behind the scenes. Your agents only need a single endpoint token to securely access the MCP Server cluster.

The coordinator agent can call `get_usage_stats` to monitor consumption. It can then pause tasks or use `list_active_sessions` to clean up old processes.

All HTML content, screenshots, and PDFs are processed in volatile memory within a secure V8 isolate. Vinkius immediately discards all session data as soon as the tool execution finishes.

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