How to Use the Browse AI MCP in AutoGen

Q: How do AutoGen agents share Browse AI task results?

One agent calls gettaskdata to retrieve the JSON payload and posts it to the group chat. Other specialized agents can then read, analyze, or validate that data in the same conversation.

Q: Can AutoGen agents manage Browse AI limits?

Yes, your agents can call listcredits to check remaining runs. A budget agent can block a planned runbulktask if the credit cost exceeds your set threshold.

Q: How does AutoGen handle errors during Browse AI extractions?

If gettask returns a failed status, the executing agent flags the error in the chat. A debugger agent can then inspect the target URL or parameters to attempt a retry.

Let your AutoGen agents coordinate web scraping tasks and debate extraction results in real time using this managed 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 Browse AI MCP to AutoGen

Create your Vinkius account to connect Browse 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 Browse AI with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative Scraping Execution

The `run_robot` tool allows your primary coordinator agent to initiate a web scrape based on user requests. Once triggered, the agent passes the resulting task ID to a monitoring agent for follow-up. The monitoring agent then uses this MCP Server to track progress while a third agent prepares to analyze the incoming data. This multi-agent coordination ensures that scraping tasks never block your main conversation loop.

Consensus-Driven Bulk Extraction

The `run_bulk_task` tool runs complex, multi-URL extractions across your target list. Your AutoGen agents can debate which URLs are high-priority before passing the final list to the tool. After execution, a data analyst agent uses `download_bulk_data` to pull the results. A separate validator agent then reviews the JSON payload to check for errors or missing fields before accepting the run.

Dynamic Monitor Selection

The `list_monitors` tool lets your agents inspect active web monitors to see what data is already being captured. This prevents your agents from running duplicate scraping tasks on the same target pages. If a monitor is missing, the agents can look up configurations using `get_robot` to decide how to set up a new run. They coordinate to optimize your credit usage by checking `list_credits` first.

Setup guide

Set up Browse 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 Browse 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="Browse AI_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

One agent calls `get_task_data` to retrieve the JSON payload and posts it to the group chat. Other specialized agents can then read, analyze, or validate that data in the same conversation.

Yes, your agents can call `list_credits` to check remaining runs. A budget agent can block a planned `run_bulk_task` if the credit cost exceeds your set threshold.

If `get_task` returns a failed status, the executing agent flags the error in the chat. A debugger agent can then inspect the target URL or parameters to attempt a retry.

You register our endpoint using the AutoGen MCP adapter package. This instantly maps all ten scraping tools to your agent's capabilities list.

All scraped JSON payloads, task details, and credit logs are processed in an isolated V8 sandbox. The MCP Server operates with zero-trust protocols, ensuring your sensitive scraping targets remain secure.

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