How to Use the AccuWeather MCP in LangChain

Q: How do I pass AccuWeather location keys between LangChain tools?

Set up a chain where the output of searchlocation feeds directly into the input of getcurrentconditions. LangChain's ReAct agent handles this transition by extracting the key from the search results and using it for the next query.

Q: Can I monitor AccuWeather API latency inside LangChain?

Yes, you can use LangSmith to trace every call made to gethourlyforecast or other tools. It logs the exact execution time, token count, and raw payload returned by the server.

Q: How do I handle AccuWeather metric conversions in LangChain?

You can force your chain to use getcurrentconditionsmetric when the user requests Celsius. The agent chooses this MCP tool based on the prompt context, ensuring your chain outputs the correct units.

Q: What happens if a location search returns multiple keys?

Your agent will review the list of cities returned by searchlocation and use administrative area details to pick the correct match. It then passes that specific key to getdailyforecast.

Chain AccuWeather metrics directly into your LangChain agents to make weather-dependent decisions on the fly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AccuWeather MCP to LangChain

Create your Vinkius account to connect AccuWeather 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 AccuWeather with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Route weather data through LangChain pipelines

Your LangChain agent can resolve locations on its own before pulling weather data. It starts by running `search_location` to fetch the right key, then feeds that key directly into `get_current_conditions` to check local temperature and humidity. This means you don't have to hardcode location IDs. The agent handles the lookup and passing of arguments in a single run, making your pipelines dynamic and resilient to messy user inputs.

Trace AccuWeather tool outputs in LangSmith

When your agent checks `get_weather_alarms` to see if a storm is coming, you can watch the entire decision-making process live. LangSmith traces every step, showing you exactly what raw JSON payload came back from the AccuWeather MCP Server. This visibility prevents silent failures. You can see the exact latency of `get_daily_forecast` calls and optimize how your chains handle heavy payload data without guessing where bottlenecks happen.

Evaluate outdoor indices inside chains

Build agents that combine external database records with AccuWeather's activity ratings. The agent runs `get_weather_indices` to check golf or flight delay risks, combining that rating with your scheduling data to automate calendar updates. By feeding `get_index_groups` into your decision logic, you let the agent discover which lifestyle metrics are available. It can then fetch indices for running, hiking, or composting without hardcoded rules.

Setup guide

Set up AccuWeather 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 AccuWeather 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({
    "accuweather-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 AccuWeather 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 AccuWeather. 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 AccuWeather 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 AccuWeather MCP in LangChain

Set up a chain where the output of `search_location` feeds directly into the input of `get_current_conditions`. LangChain's ReAct agent handles this transition by extracting the key from the search results and using it for the next query.

Yes, you can use LangSmith to trace every call made to `get_hourly_forecast` or other tools. It logs the exact execution time, token count, and raw payload returned by the server.

You can force your chain to use `get_current_conditions_metric` when the user requests Celsius. The agent chooses this MCP tool based on the prompt context, ensuring your chain outputs the correct units.

Your agent will review the list of cities returned by `search_location` and use administrative area details to pick the correct match. It then passes that specific key to `get_daily_forecast`.

Your location keys and coordinate queries are processed in an ephemeral Vinkius V8 Isolate Sandbox. No data is stored or logged on our servers, keeping your local lookups completely private from any external MCP client.

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