How to Use the PurpleAir MCP in AutoGen

Q: How do I integrate the PurpleAir MCP Server into an AutoGen agent workflow?

Use the mcpservertools function to define the server connection and pass the resulting tool list to your AssistantAgent. The McpToolAdapter will handle the schema translation for you.

Let your AutoGen agents debate and decide using live data from the PurpleAir MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect PurpleAir MCP to AutoGen

Create your Vinkius account to connect PurpleAir 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 PurpleAir with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Debate air quality findings

Deploy multiple agents to evaluate readings from `get_pm25_sensors`. One agent can analyze the data while another challenges the findings based on historical trends. This debate process ensures you aren't relying on a single sensor's potentially noisy output. The agents must reach a consensus before providing you with a final report.

Automate sensor network monitoring

Assign an agent to periodically poll `list_sensors` and flag anomalies. If the agent detects a change, it can trigger another agent to run `get_sensor_data` for a detailed check. This creates a self-correcting system. Your agents handle the routine monitoring work while you focus on the results of their internal deliberations.

Negotiate data-driven actions

Build a team where a security agent reviews the source of `get_sensors_near_me` results before a performance agent processes them. They negotiate the reliability of the data sources. This prevents your system from acting on uncalibrated or unreliable sensor readings. It is a robust way to handle multi-agent decision-making in real-world environments.

Setup guide

Set up PurpleAir 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 PurpleAir 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="PurpleAir_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use the mcp_server_tools function to define the server connection and pass the resulting tool list to your AssistantAgent. The McpToolAdapter will handle the schema translation for you.

They can. By giving multiple agents access to the same toolset, they can compare results from different sensors and debate the accuracy of the readings.

Yes. It works with both stdio and HTTP transports, allowing your agents to communicate with the server regardless of how you structure your multi-agent conversation.

The adapter automatically provides the tool schemas to your agents. This allows them to correctly select `get_sensor_data` or `get_sensors_near_me` during their conversation.

The connection is established through an ephemeral sandbox. No sensitive user data is stored, and the server only interacts with public sensor information and atmospheric metrics.

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