How to Use the Nimbleway MCP in AutoGen

Q: How do I load Nimbleway into AutoGen?

Install the autogen-extmcp package. Fetch the tools using mcpservertools with your endpoint, then inject them into your AssistantAgent configuration.

Q: Should my agents read raw HTML?

Usually no. The extracthtml MCP tool consumes massive amounts of token context. Stick to extractmarkdown unless your agents specifically need to analyze DOM structures.

Equip your AutoGen multi-agent teams with enterprise web scraping capabilities.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nimbleway MCP to AutoGen

Create your Vinkius account to connect Nimbleway 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 Nimbleway with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Deploy researcher agents with this MCP Server

Give one agent the job of finding information. It uses `search_web` to scan the internet for specific topics. It compiles a list of URLs and hands them off to a specialized scraper agent. The scraper agent executes `extract_markdown` on the targets. If the content looks thin, a critic agent flags the poor quality. The team debates the results and decides whether to run a new search or accept the data.

Manage proxy networks collaboratively

Scraping at scale requires infrastructure awareness. Your operations agent can monitor `list_proxies` via the MCP connection to ensure the team uses the correct IP rotation for specific regional domains. Before kicking off a massive data harvest, a manager agent checks `get_account_usage`. If the team is close to its bandwidth limit, it negotiates with the researcher agents to prioritize only the most critical URLs.

Track complex pipeline states

Long-running data collection tasks require oversight. Your agents don't have to sit idle while waiting for a heavy page to render. They can trigger the task and periodically check `get_job` for updates. For recurring tasks, the team reviews `list_pipelines` and `get_pipeline`. They analyze the performance of existing scraping setups and propose adjustments to improve success rates.

Setup guide

Set up Nimbleway 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 Nimbleway 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="Nimbleway_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Install the `autogen-ext[mcp]` package. Fetch the tools using `mcp_server_tools` with your endpoint, then inject them into your `AssistantAgent` configuration.

Yes. You can provide the same toolset to an entire group chat. A researcher might run the searches while a different agent handles the actual extraction.

The agent receives the error from the tool. It can then check `get_me` to verify account status or retry the request with a different proxy configuration.

Usually no. The `extract_html` MCP tool consumes massive amounts of token context. Stick to `extract_markdown` unless your agents specifically need to analyze DOM structures.

Your proxy settings and account usage data remain entirely isolated. The Vinkius runtime uses ephemeral sandboxing, ensuring no raw search results or credentials leak between sessions or persist on disk.

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