Kommody

Commodity data in Claude, ChatGPT and Cursor via MCP

Kommody runs a remote MCP (Model Context Protocol) server, so AI assistants such as Claude, ChatGPT and Cursor can query its commodity data directly: crop-weighted weather, CFTC positioning, market news and prediction markets. You add one URL as a connector and sign in with your Kommody account; no API key to copy.

By the Kommody team · Updated

How to connect

In Claude, open Settings → Connectors → Add custom connector and paste the Kommody MCP URL, https://kommody.com/api/mcp. In ChatGPT, create a connector in Settings → Connectors (developer mode) with OAuth. In Claude Code, run claude mcp add --transport http kommody followed by the URL. Cursor, VS Code and other clients take the same URL in their MCP config.

The first time the assistant calls a tool, your browser opens the Kommody sign-in and you press Allow. Step-by-step guides for each client are on the Connect page after sign-up.

What you can ask

Once connected, ask in plain language and the assistant pulls the numbers it needs:

  • Is the weather in Brazil a risk for soybeans in the next 14 days?
  • Compare speculators' net position in cocoa with the last 3 years.
  • What are the most bullish corn news today, and why?

Python and Excel

Every chart in Kommody can also be downloaded as CSV or Excel, and the same endpoints can be called from Python with your login, so the data fits into existing models and spreadsheets.

Frequently asked questions

What is MCP?
The Model Context Protocol is an open standard that lets AI assistants call external tools and data sources. A remote MCP server like Kommody's works in any client that supports it.
Do I need an API key?
No. AI assistants sign in through your browser with OAuth. Python and Excel use your Kommody login.

Related

See it with live data in Kommody

Weather, news, positioning and prediction markets for the commodities you follow, in one dashboard or in your AI assistant.