How to Use the AerisWeather MCP in LlamaIndex

Q: How do I index AerisWeather forecasts into LlamaIndex?

You use the getforecasts tool within your LlamaIndex pipeline to retrieve raw JSON weather data. The framework then parses this payload into document nodes, which are embedded and stored in your vector database.

Q: Can LlamaIndex query historical AerisWeather data for RAG?

Yes, your LlamaIndex agent can call getconditions to fetch historical data dating back to 2004. This data is indexed immediately, allowing your agent to perform semantic searches over decades of weather records.

Q: How does the AerisWeather MCP Server handle geographical lookups in LlamaIndex?

The getplaces tool translates natural language city names in your LlamaIndex queries into exact coordinates. This allows your agent to fetch precise observations for the specific regions your users ask about.

Q: Can I filter precipitation forecasts using this server?

Yes, you can pass the minutely precipitation filter to the getconditions tool. This lets your agent index high-resolution, short-term rain forecasts directly into your active context.

Index live AerisWeather data into your LlamaIndex vector stores for grounded, hallucination-free RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AerisWeather MCP to LlamaIndex

Create your Vinkius account to connect AerisWeather to LlamaIndex 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 AerisWeather with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index `get_conditions` data into LlamaIndex memory

The `get_conditions` tool feeds hyper-local precipitation and historical weather data directly into your LlamaIndex vector store using this MCP Server. Your indexer converts these live metrics into searchable document nodes, allowing your agent to query past weather patterns without hallucinating facts. By querying this tool, your RAG pipeline blends real-time atmospheric conditions with your private data source files. This ensures your weather-dependent search queries are always grounded in actual physical measurements.

Ground RAG queries with live `get_forecasts`

The `get_forecasts` tool updates your LlamaIndex query engine with forward-looking weather predictions. Instead of relying on static training data, your agent pulls active forecasts to answer complex questions about upcoming regional conditions. You can set up a local vector index that automatically updates its context window using this tool. This prevents your agent from serving stale predictions to users asking about tomorrow's conditions.

Query geographical data using LlamaIndex and MCP Server tools

The `get_places` tool resolves city names, airport codes, and station IDs into structured coordinates for your LlamaIndex agent. Your agent uses this geographical mapping to index weather data points precisely where they belong in your vector database. Combined with `get_observations`, this tool lets your agent build a localized knowledge graph of weather conditions. This makes it easy to run semantic searches across different meteorological stations without manual mapping.

Setup guide

Set up AerisWeather MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all AerisWeather MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to AerisWeather tools.",
)
response = await agent.run("List recent AerisWeather data")

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 AerisWeather. 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 AerisWeather 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 AerisWeather MCP in LlamaIndex

You use the `get_forecasts` tool within your LlamaIndex pipeline to retrieve raw JSON weather data. The framework then parses this payload into document nodes, which are embedded and stored in your vector database.

Yes, your LlamaIndex agent can call `get_conditions` to fetch historical data dating back to 2004. This data is indexed immediately, allowing your agent to perform semantic searches over decades of weather records.

The `get_places` tool translates natural language city names in your LlamaIndex queries into exact coordinates. This allows your agent to fetch precise observations for the specific regions your users ask about.

Yes, you can pass the minutely precipitation filter to the `get_conditions` tool. This lets your agent index high-resolution, short-term rain forecasts directly into your active context.

All coordinate lookups and station IDs processed by the MCP Server run inside isolated V8 sandboxes. Your geographical search parameters are discarded the moment the API call completes, leaving zero persistent logs.

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