How to Use the Olostep MCP in AutoGen

Debate and scrape with AutoGen. Let Olostep provide the data for your multi-agent conversations and consensus-based decisions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Olostep MCP to AutoGen

Create your Vinkius account to connect Olostep to AutoGen — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Olostep with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Drive agent debates with real-time data

Give your agents the ability to verify claims by fetching live web data. When agents disagree, one can trigger `scrape_url` to settle the argument with current facts. This adds a layer of objective truth to your multi-agent system. The agents negotiate based on the actual content retrieved rather than relying on internal model training data.

Coordinate bulk tasks between agents

Assign a dedicated scraping agent to handle heavy lifting with `create_batch`. Other agents can monitor the status using `list_batches` and wait for the results before continuing their discussion. This separation of duties allows your system to process complex information without stalling the core conversation. Your agents remain productive while waiting for the data to arrive.

Manage scraping infrastructure via agents

Control your scraping agents through conversation. If a task requires a new configuration, your lead agent can use `create_agent` to set up a specialized scraper on the fly. This dynamic approach lets your system adapt to new targets without human intervention. The agents manage the tools they need to complete their assigned objectives.

Setup guide

Set up Olostep 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 Olostep 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="Olostep_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

The server tools are injected into your assistant agents as function calls. The agents then decide through their own reasoning when to trigger a scrape or check a batch status.

Yes, the tools are shared across the agent group. You can define specific permissions so that only the designated scraping agent is responsible for calling the tools.

The agent receives the error message from the tool call. It can then report the failure to the group, discuss the issue, and decide whether to try a different URL or fix the request.

You can include a monitoring agent in your group. This agent periodically calls `get_usage` to provide updates on your credit consumption to the rest of the team.

Your API tokens and scraping target list are used only for the tasks you define. The data retrieved from the web is passed directly to your agents and is not logged by the infrastructure providers.

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