Mint a token, paste it into Claude, ChatGPT desktop, or any Model Context Protocol client, and that client can reach ThatApp's tools and your connectors directly.
Platform tools at one surface and a meta-dispatch interface to your iPaaS connector library at another. Your AI client can query, build, and report.
Issue tokens from your dashboard and revoke them when you are done. A leaked token is recoverable, honored within about sixty seconds.
Each token is scoped to a specific surface, so a token for one cannot be reused for the other. Destructive cross-tenant tools are intentionally disabled.
Stdio for local clients like Claude Desktop, and streamable HTTP for remote web clients. Use whichever your client supports.
Issue a scoped token from your ThatApp dashboard in a couple of clicks.
Paste the endpoint and token into Claude, ChatGPT desktop, or any MCP client.
Your assistant can now query your data lake, manage flows, and read usage.
The public tool surface is aimed at consulting partners and developers building on top of ThatApp. Per-user scoped tokens and metered rate limits are on the roadmap. If you are building something ambitious, talk to us and we will set you up properly.