How to Use the Tomorrow.io Extended MCP in AutoGen

Q: Can I combine multiple data sources with Tomorrow.io Extended and AutoGen?

Yes. You can give one agent access to getweatherforecast and another access to external documents. They then debate how the forecast applies to the documented policy, leading to a risk assessment.

Get consensus on risk using Tomorrow.io Extended and AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Tomorrow.io Extended MCP to AutoGen

Create your Vinkius account to connect Tomorrow.io Extended 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 Tomorrow.io Extended with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debating weather risks with the MCP Server.

Need to know if construction is safe? You can set up multiple agents: a 'Safety Agent' calls `list_weather_alerts` while a 'Project Manager Agent' checks `get_weather_forecast`. They then debate which conclusion is correct. The goal here isn't just an answer; it's consensus. The system forces competing perspectives to negotiate and converge on the final, safest decision.

Analyzing air quality using AutoGen.

You can have one agent monitor `get_air_quality` while another checks for related industrial warnings via an internal source. They challenge each other's initial findings about the pollution levels. This conversational flow is useful when the answer isn't obvious and requires multiple viewpoints to weigh risk.

Consensus on historical weather using AutoGen.

If you need to know why an event happened, one agent pulls `get_recent_history`. A second agent then cross-references that with the specific date's alerts by calling `list_weather_alerts`. The debate forces a comparison: Did the history show high winds, or was it just low visibility that caused the issue? AutoGen resolves this conflict.

Setup guide

Set up Tomorrow.io Extended 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 Tomorrow.io Extended 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="Tomorrow.io Extended_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Tomorrow.io Extended 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="Tomorrow.io Extended_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Tomorrow.io Extended 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 Tomorrow.io. 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 Tomorrow.io Extended 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 Tomorrow.io Extended MCP in AutoGen

AutoGen doesn't run a single query; it runs a deliberation. Multiple agents debate the data gathered from MCP tools like `get_realtime_weather` until they agree on the final conclusion or identify conflicting risks.

This server touches air quality, forecasts, and alerts. When using it with AutoGen, agents are debating specific metrics—like the severity level of a weather alert or the current pollutant concentration.

Yes. You can give one agent access to `get_weather_forecast` and another access to external documents. They then debate how the forecast applies to the documented policy, leading to a risk assessment.

It is perfect for it. If your business involves high stakes—say, shutting down operations due to weather—you need the negotiation and deliberation that multiple agents provide.

The framework manages the entire conversation state. You get a full transcript of every argument, challenge, and tool call, letting you trace exactly how consensus was reached.

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