Claude.ai Agent exit execution for self-procured services exit_probe
How to: Claude.ai Agent exit execution for self-procured services exit_probe
Add Agent exit execution for self-procured services to Claude.ai
-
01
Open Settings → Connectors → Add custom connector and merge this in. Keep any servers already there.
https://textforagents.com/products/agent-exit-offboarding-execution/mcp-
02
Save the file and restart Claude.ai.
-
03
Ask for something exit_probe does. Claude.ai lists the server's tools on connect and calls exit_probe itself — you do not invoke it by name.
-
04
If nothing happens, check the server is running and that Agent exit execution for self-procured services's identifier in your config matches the one above exactly.
Claude on the web takes a remote URL and completes OAuth in the browser. For a packaged server use Claude Desktop or Claude Code instead. Claude.ai docs
Same tool, other clients
This list was read from the server itself, by connecting to it and calling tools/list on 21 October 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.