How to Use the Tomorrow.io Plus MCP in AutoGen

Q: How do I get multiple weather perspectives with Tomorrow.io Plus and AutoGen?

Assign different roles to your agents. One agent can check listinsights for high-level categories, while another uses getforecastweather. They'll debate which insight is most relevant.

Achieve weather consensus across multiple viewpoints using AutoGen agents and the 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 Tomorrow.io Plus MCP to AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debating Forecasts with AutoGen

Want an answer that survives debate? Have one agent pull a long-term outlook using `get_forecast_weather`. A second agent can challenge that projection by calling `get_realtime_weather` to argue for the immediate state. The agents then negotiate, converging on the most accurate short-term prediction based on both inputs.

Consensus over Weather Events with AutoGen

When deciding if a trip is viable, agents can debate risk. One agent checks `list_events` for predicted weather events, while another calls `get_map_tile` to visualize the physical impact of those events. The system doesn't just return data; it reaches a conclusion about travel viability based on the deliberation.

Defining Scope with MCP Server

Agents need clear boundaries. They can use `list_locations` to define potential areas, and then collaborate using `get_recent_history_weather`. The conversation narrows down from a list of all locations to the specific historical data required. This ensures that every step in the multi-agent flow is grounded by concrete input.

Setup guide

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

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

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

Assign different roles to your agents. One agent can check `list_insights` for high-level categories, while another uses `get_forecast_weather`. They'll debate which insight is most relevant.

Yes. You can set up a conflict: Agent A calls for current conditions using `get_realtime_weather`, and Agent B challenges that by asking for historical data via `get_recent_history_weather`.

Use a multi-agent discussion where one agent lists potential areas (`list_locations`), and another uses `post_timelines` to process weather data over complex GeoJSON geometries.

It does. You can structure a debate where one agent gets a general forecast (`get_forecast_weather`) and another runs specific alerts checks (`list_alerts`), forcing consensus on risk levels.

This server touches structured weather data, including current conditions and historical records spanning temperature and precipitation intensity. All tool calls are processed through Vinkius's secure endpoint token.

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