SIGN UPLOG IN
X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Openweather api MCP with Pydantic AI

Connect Pydantic AI to Openweather api MCP. Get current weather in paris right now, show 5-day forecast for san francisco, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Openweather api logoOpenweather api
Api Key

Openweather api provides global weather data, forecasts, and climate history. Instantly access accurate, location-based weather insights for any app or workflow.

21 Tools

Introduction

This guide walks you through connecting Openweather api to Pydantic AI using the Composio tool router. By the end, you'll have a working Openweather api agent that can get current weather and forecasts, check air pollution and UV index, geocode locations, and manage weather stations through natural language commands.

This guide will help you understand how to give your Pydantic AI agent real control over a Openweather api account through Composio's Openweather api MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Openweather api with

Claude CodeCursorChatGPTClaude CoworkAntigravityOpenAI Agents SDKClaude Agent SDKCodexGrok BuildVS CodeOpenCodeOpenClawHermesAtomic AgentPiDeepSeek HarnessGoogle ADKLangChainVercel AI SDKMastra AILlamaIndexCrewAIAutoGen

TL;DR

Here's what you'll learn:
  • How to set up your Composio API key and User ID
  • How to create a Composio Tool Router session for Openweather api
  • How to attach an MCP Server to a Pydantic AI agent
  • How to stream responses and maintain chat history
  • How to build a simple REPL-style chat interface to test your Openweather api workflows

What is Pydantic AI?

Pydantic AI is a Python framework for building AI agents with strong typing and validation. It leverages Pydantic's data validation capabilities to create robust, type-safe AI applications.

Key features include:

  • Type Safety: Built on Pydantic for automatic data validation
  • MCP Support: Native support for Model Context Protocol servers
  • Streaming: Built-in support for streaming responses
  • Async First: Designed for async/await patterns

What is the Openweather api MCP server, and what's possible with it?

The Openweather api MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Openweather api account. It provides structured and secure access to real-time, forecasted, and historical weather data, so your agent can fetch current conditions, deliver forecasts, analyze air quality, and perform location-based weather insights on your behalf.

  • Current weather retrieval: Instantly get up-to-the-minute weather details for any city or geographic coordinate, including temperature, humidity, and wind.
  • Five-day weather forecasting: Ask your agent for detailed 5-day forecasts in 3-hour intervals to plan events, travel, or outdoor activities.
  • Air pollution and UV index analysis: Retrieve current, forecasted, and historical air pollution data, as well as UV index values, to monitor environmental quality for any location.
  • Geocoding and reverse geocoding: Convert location names to coordinates or find city/state information from latitude and longitude, enabling location-aware weather queries.
  • Radius-based weather search: Fetch weather conditions for all cities within a specified radius around a geographic point for broader regional analysis.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Step by step09 STEPS
1

Prerequisites

Before starting, make sure you have:
  • Python 3.9 or higher
  • A Composio account with an active API key
  • Basic familiarity with Python and async programming
2

Getting API Keys for OpenAI and Composio

OpenAI API Key
  • Go to the OpenAI dashboard and create an API key. You'll need credits to use the models, or you can connect to another model provider.
  • Keep the API key safe.
Composio API Key
  • Log in to the Composio dashboard.
  • Navigate to your API settings and generate a new API key.
  • Store this key securely as you'll need it for authentication.
3

Install dependencies

bash
pip install composio pydantic-ai python-dotenv

Install the required libraries.

What's happening:

  • composio connects your agent to external SaaS tools like Openweather api
  • pydantic-ai lets you create structured AI agents with tool support
  • python-dotenv loads your environment variables securely from a .env file
4

Set up environment variables

bash
COMPOSIO_API_KEY=your_composio_api_key_here
USER_ID=your_user_id_here
OPENAI_API_KEY=your_openai_api_key

Create a .env file in your project root.

What's happening:

  • COMPOSIO_API_KEY authenticates your agent to Composio's API
  • USER_ID associates your session with your account for secure tool access
  • OPENAI_API_KEY to access OpenAI LLMs
5

Import dependencies

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()
What's happening:
  • We load environment variables and import required modules
  • Composio manages connections to Openweather api
  • MCPServerStreamableHTTP connects to the Openweather api MCP server endpoint
  • Agent from Pydantic AI lets you define and run the AI assistant
6

Create a Tool Router Session

python
async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Openweather api
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["openweather_api"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")
What's happening:
  • We're creating a Tool Router session that gives your agent access to Openweather api tools
  • The create method takes the user ID and specifies which toolkits should be available
  • The returned session.mcp.url is the MCP server URL that your agent will use
7

Initialize the Pydantic AI Agent

python
# Attach the MCP server to a Pydantic AI Agent
openweather_api_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
agent = Agent(
    "openai:gpt-5",
    toolsets=[openweather_api_mcp],
    instructions=(
        "You are a Openweather api assistant. Use Openweather api tools to help users "
        "with their requests. Ask clarifying questions when needed."
    ),
)
What's happening:
  • The MCP client connects to the Openweather api endpoint
  • The agent uses GPT-5 to interpret user commands and perform Openweather api operations
  • The instructions field defines the agent's role and behavior
8

Build the chat interface

python
# Simple REPL with message history
history = []
print("Chat started! Type 'exit' or 'quit' to end.\n")
print("Try asking the agent to help you with Openweather api.\n")

while True:
    user_input = input("You: ").strip()
    if user_input.lower() in {"exit", "quit", "bye"}:
        print("\nGoodbye!")
        break
    if not user_input:
        continue

    print("\nAgent is thinking...\n", flush=True)

    async with agent.run_stream(user_input, message_history=history) as stream_result:
        collected_text = ""
        async for chunk in stream_result.stream_output():
            text_piece = None
            if isinstance(chunk, str):
                text_piece = chunk
            elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                text_piece = chunk.delta
            elif hasattr(chunk, "text"):
                text_piece = chunk.text
            if text_piece:
                collected_text += text_piece
        result = stream_result

    print(f"Agent: {collected_text}\n")
    history = result.all_messages()
What's happening:
  • The agent reads input from the terminal and streams its response
  • Openweather api API calls happen automatically under the hood
  • The model keeps conversation history to maintain context across turns
9

Run the application

python
if __name__ == "__main__":
    asyncio.run(main())
What's happening:
  • The asyncio loop launches the agent and keeps it running until you exit

Complete Code

Here's the complete code to get you started with Openweather api and Pydantic AI:

python
import asyncio
import os
from dotenv import load_dotenv
from composio import Composio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerStreamableHTTP

load_dotenv()

async def main():
    api_key = os.getenv("COMPOSIO_API_KEY")
    user_id = os.getenv("USER_ID")
    if not api_key or not user_id:
        raise RuntimeError("Set COMPOSIO_API_KEY and USER_ID in your environment")

    # Create a Composio Tool Router session for Openweather api
    composio = Composio(api_key=api_key)
    session = composio.create(
        user_id=user_id,
        toolkits=["openweather_api"],
    )
    url = session.mcp.url
    if not url:
        raise ValueError("Composio session did not return an MCP URL")

    # Attach the MCP server to a Pydantic AI Agent
    openweather_api_mcp = MCPServerStreamableHTTP(url, headers={"x-api-key": COMPOSIO_API_KEY})
    agent = Agent(
        "openai:gpt-5",
        toolsets=[openweather_api_mcp],
        instructions=(
            "You are a Openweather api assistant. Use Openweather api tools to help users "
            "with their requests. Ask clarifying questions when needed."
        ),
    )

    # Simple REPL with message history
    history = []
    print("Chat started! Type 'exit' or 'quit' to end.\n")
    print("Try asking the agent to help you with Openweather api.\n")

    while True:
        user_input = input("You: ").strip()
        if user_input.lower() in {"exit", "quit", "bye"}:
            print("\nGoodbye!")
            break
        if not user_input:
            continue

        print("\nAgent is thinking...\n", flush=True)

        async with agent.run_stream(user_input, message_history=history) as stream_result:
            collected_text = ""
            async for chunk in stream_result.stream_output():
                text_piece = None
                if isinstance(chunk, str):
                    text_piece = chunk
                elif hasattr(chunk, "delta") and isinstance(chunk.delta, str):
                    text_piece = chunk.delta
                elif hasattr(chunk, "text"):
                    text_piece = chunk.text
                if text_piece:
                    collected_text += text_piece
            result = stream_result

        print(f"Agent: {collected_text}\n")
        history = result.all_messages()

if __name__ == "__main__":
    asyncio.run(main())

Conclusion

You've built a Pydantic AI agent that can interact with Openweather api through Composio's Tool Router. With this setup, your agent can perform real Openweather api actions through natural language. You can extend this further by:
  • Adding other toolkits like Gmail, HubSpot, or Salesforce
  • Building a web-based chat interface around this agent
  • Using multiple MCP endpoints to enable cross-app workflows (for example, Gmail + Openweather api for workflow automation)
This architecture makes your AI agent "agent-native", able to securely use APIs in a unified, composable way without custom integrations.
TOOLS

Supported Tools

Every Openweather api action and event your agent gets out of the box.

Delete Weather Station

Tool to delete a registered weather station.

Get 5 Day Forecast

Get a 5-day forecast at 3-hour intervals for a location identified by city name, city ID, postal code, or coordinates.

Get Current Air Pollution Data

Tool to fetch current air pollution data for a location.

Get Air Pollution Forecast

Tool to get forecasted air pollution data for a specific location.

Get Air Pollution History

Tool to retrieve historical air pollution data.

Get Circle City Weather

Search for current weather data in cities around a geographic point, with an optional number of cities to return.

Get Current Weather

Retrieve current weather for a location identified by city name, city ID, postal code, or coordinates.

Get Geocoding by Zip Code

Tool to convert zip/post code into geographic coordinates.

Get Direct Geocoding

Tool to convert a location name into geographic coordinates.

Get Reverse Geocoding

Tool to convert geographic coordinates into a location name.

Get Station Measurements

Tool to retrieve aggregated measurements from a weather station with minute, hour, or day granularity.

Get Current UV Index

Tool to retrieve current UV index for a location.

Get UV Index Forecast

Tool to retrieve UV index forecast for a specific location.

Get UV Index History

Tool to retrieve historical UV index data for a specified location and time range.

Get Weather Map Tile (2.0)

Tool to fetch Weather Maps 2.

Get Weather Station

Tool to get information about a specific weather station by its ID.

Get Weather Stations

Tool to list all weather stations added to your account.

Get Weather Triggers

Tool to retrieve weather triggers for specific conditions.

Add Weather Station

Tool to add a new weather station to your account.

Submit Station Measurements

Tool to submit weather measurements from a registered station.

Update Weather Station

Update an existing weather station's details, including its name, location, external ID, or altitude.

FRAMEWORKS

How to build Openweather api MCP Agent with another framework

Claude Code logo

Claude Code

Use Openweather api MCP with Claude Code

Cursor logo

Cursor

Use Openweather api MCP with Cursor

ChatGPT logo

ChatGPT

Use Openweather api MCP with ChatGPT

Claude Cowork logo

Claude Cowork

Use Openweather api MCP with Claude Cowork

Antigravity logo

Antigravity

Use Openweather api MCP with Antigravity

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Openweather api MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Openweather api MCP with Claude Agent SDK

Codex logo

Codex

Use Openweather api MCP with Codex

Grok Build logo

Grok Build

Use Openweather api MCP with Grok Build

VS Code logo

VS Code

Use Openweather api MCP with VS Code

OpenCode logo

OpenCode

Use Openweather api MCP with OpenCode

OpenClaw logo

OpenClaw

Use Openweather api MCP with OpenClaw

Hermes logo

Hermes

Use Openweather api MCP with Hermes

Atomic Agent logo

Atomic Agent

Use Openweather api MCP with Atomic Agent

Pi logo

Pi

Use Openweather api MCP with Pi

DeepSeek Harness logo

DeepSeek Harness

Use Openweather api MCP with DeepSeek Harness

Google ADK logo

Google ADK

Use Openweather api MCP with Google ADK

LangChain logo

LangChain

Use Openweather api MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Openweather api MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Openweather api MCP with Mastra AI

LlamaIndex logo

LlamaIndex

Use Openweather api MCP with LlamaIndex

CrewAI logo

CrewAI

Use Openweather api MCP with CrewAI

AutoGen logo

AutoGen

Use Openweather api MCP with AutoGen

FAQ

Frequently asked questions

With a standalone Openweather api MCP server, the agents and LLMs can only access a fixed set of Openweather api tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Openweather api and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Pydantic AI fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Openweather api tools.

Yes, absolutely. You can configure which Openweather api scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Openweather api data and credentials are handled as safely as possible.

Start with Openweather api.It takes 30 seconds.

Managed auth, hosted MCP servers, and every Openweather api tool your agent needs.Free to start.

Start building