Migrate from Webhook.site
Move from Webhook.site to HookSense in 15 minutes.
If you've been pasting Webhook.site URLs to eyeball requests by hand, HookSense moves you up a layer: your AI agent creates a callback endpoint and awaits the signed result over MCP with wait_for_callback — no polling, no tab to watch.
Step 1 · Install the HookSense MCP server
- 1Run `npx @hooksense/mcp` and add it to Claude or Cursor.
- 2Have your agent call create_callback_endpoint to get a signed callback URL.
- 3Keep your old Webhook.site URL running in parallel — there's no rush.
Step 2 · Map features
| In Webhook.site | In HookSense |
|---|---|
| Random URL `webhook.site/abc-123` | Agent-created callback endpoint via create_callback_endpoint |
| Watch the page for requests | Agent calls wait_for_callback and blocks until the signed result arrives |
| Manual signature checks | verify_signature built into the MCP toolset |
| Custom response (Pro) | Custom response (Hook+) — same idea |
| Email capture | Not supported — keep Webhook.site for that one workflow |
Step 3 · Things to know
- HookSense is agent-native: instead of a human watching a tab, your agent awaits the result over MCP. The mental shift matters more than the migration steps.
- Inspection still exists — list_callbacks and get_callback_payload let you see what landed — but the core value is the wait_for_callback primitive.
- Webhook.site's email-to-webhook feature has no HookSense equivalent. If you rely on it, keep that workflow on Webhook.site and use HookSense for agent callbacks.
Zero-downtime migration
Install `npx @hooksense/mcp`, have your agent create a callback endpoint, and call wait_for_callback for the result. Free to start; request early access for paid plans.
Get a callback URL