Yes, with one wrinkle. ChatGPT added Model Context Protocol support in September 2025 through Developer Mode and connectors, but it connects to remote MCP servers over HTTP, not the local one used with Claude. So you either host the same Hostfully MCP server at an HTTPS URL and add it as a connector, or wire the Hostfully Platform API into a custom GPT as an Action.
What works today
According to OpenAI, ChatGPT's Developer Mode, available on paid plans, provides full MCP client support for both read and write tools. The tools and the underlying Hostfully Platform API are identical to the Claude setup, so the work you do once carries over: only the transport changes from local (stdio) to remote (HTTP).
Hostfully is one of the easier platforms to do this with, because the Platform API authenticates with a single header (your API key) rather than an OAuth token flow, so the hosted version of the server has no extra moving parts. Build the read-only server from our Claude guide first, confirm it works locally, then host it and point ChatGPT's connector at the URL.
The hosted API route
If you would rather call an API than run and maintain a server, there is a hosted middle path: the RapidEye API exposes Hostfully as a hosted connector, so the credential handling and token care above happen on our side and your assistant or script calls one consistent surface. The catalogue is machine-readable, which means an AI agent can discover it and hand you the next step on its own.