Talk to an expert

MCP (Model Context Protocol)

The Meteomatics MCP (Model Context Protocol) server allows AI agents to securely access Meteomatics weather data tools. MCP is an open standard that lets AI applications connect to external tools and data sources. With the Meteomatics MCP, agents can request weather data directly from the Meteomatics API through a secure /mcp endpoint.

The MCP server manages authentication using OAuth (client registration, authorization code + PKCE, and refresh tokens). Once connected, the AI agent can access data, models, parameters, time ranges that are available to your Meteomatics API account.

MCP Server Endpoint

https://mcp.meteomatics.com/mcp

Connecting the MCP Server

To use Meteomatics weather data within your AI agent, add the Meteomatics MCP server as an external connector.

Claude

Navigate to Settings → Connectors and paste the MCP server URL.

ChatGPT

Enable Developer Mode in ChatGPT and add the Meteomatics MCP server as a custom connector:

  1. Open Settings
  2. Navigate to Connectors
  3. Enable Developer Mode
  4. Select Add Connector
  5. Paste the MCP server URL:
https://mcp.meteomatics.com/mcp

After connecting, ChatGPT can directly access Meteomatics weather tools through MCP.

Additional information about ChatGPT MCP integrations is available in the OpenAI documentation: Building MCP servers for ChatGPT Apps and API integrations .

Codex

Add the MCP server to your mcp_servers configuration: 

{
  "type": "url",
  "url": "https://mcp.meteomatics.com/mcp",
  "name": "meteomatics"
}

Authentication

The MCP server uses your Meteomatics API credentials. You will be prompted to authenticate when connecting for the first time.

Learn More

For more background on MCP and a step-by-step guide on how to use the Meteomatics MCP with an AI agent, see: How to use the Meteomatics MCP with an AI agent .

Requirements

  • An MCP-compatible AI client such as Claude, ChatGPT, or Codex