How to Use the Tomorrow.io Extended MCP in LangChain

Q: How do I ensure persistence when using Tomorrow.io Extended and LangChain?

You use client.session() to establish a persistent context, allowing your agent to remember data or parameters across multiple discrete calls instead of starting from scratch every time.

Build dynamic weather agents with LangChain.

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 LangChain

Create your Vinkius account to connect Tomorrow.io Extended to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chaining MCP Server tools in LangChain.

Need to plan an outdoor event? First, call `get_weather_forecast` for the date range. Then, pass that forecast output into a second step where you run `list_weather_alerts`. This lets your agent automatically check if any major warnings conflict with the planned activity. The LangChain framework builds these multi-step reasoning pipelines. The tool output from one function becomes the input for the next, letting your agent decide which tools to call and in what order based on intermediate results.

Checking air quality across a sequence of steps.

If you're building an agent that handles multiple sites, it can check `get_air_quality` for different zip codes sequentially. The agent keeps track of which location was checked and what the reading was. This setup is perfect for complex data gathering where one piece of information—like a poor air quality score—triggers the need to call another tool, like getting the current weather.

Retrieving historical trends using LangChain.

You can build a chain that first gets recent history via `get_recent_history`. Then, you feed those dates and locations into a separate call to `get_weather_forecast` for comparison. The agent doesn't just run tools; it compares the data. It lets you see patterns by linking past conditions directly against future predictions.

Setup guide

Set up Tomorrow.io Extended MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Tomorrow.io Extended tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "tomorrowio-extended-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Tomorrow.io Extended transactions"
    })
    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 LangChain

LangChain handles this by treating every MCP tool call as a link in a chain. You don't write one giant query; you build a sequence of steps. The agent decides which tools to use and in what order, making the process very reliable.

This MCP Server touches real-time weather conditions, including air quality metrics and historical records. When using it with LangChain, your agent's state holds temporary tool inputs and outputs.

Yes. The framework supports combining MCP tools with databases or vector stores in the same chain. You can get the weather forecast, then look up local regulations from a database, all within one single agent run.

Absolutely. Since you're building stateless agents by default, your client can manage context for multiple locations independently. You just need to feed the location parameters into each tool call.

You use `client.session()` to establish a persistent context, allowing your agent to remember data or parameters across multiple discrete calls instead of starting from scratch every time.

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