Core Feature

Debug Webhooks from
Your AI Editor

Connect Catchhook to Claude Code, Cursor, Windsurf, or Codex CLI. Your AI assistant can inspect requests, diagnose issues, replay events, and wait for new webhooks -- all without leaving your editor.

Get Started View Plans

19 Tools, One Connection

Catchhook exposes its full webhook debugging API as MCP tools. Your AI assistant can do everything you can in the dashboard -- and more.

Inspect & Filter

List and search requests by provider, event type, or signature status. Get full payload details with provider-enriched context.

Wait for Webhooks

Your AI assistant can block until a specific webhook arrives -- like waiting for a Stripe checkout event or a GitHub push.

Diagnose & Compare

Get signature analysis, setup checks, replay risk, and provider-aware diffs between any two requests.

Quick Setup

Three steps: create an API token, add the MCP server to your editor, start debugging.

Create an API Token

Go toAccount Settings and create an API token with read and write scopes.

Add to Your Editor

Claude Code

claude mcp add catchhook --transport http --url https://catchhook.app/mcp --header "Authorization: Bearer YOUR_TOKEN"

Cursor

Add to .cursor/mcp.json:

{  "mcpServers": {    "catchhook": {      "url": "https://catchhook.app/mcp",      "headers": {        "Authorization": "Bearer YOUR_TOKEN"      }    }  }}

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

{  "mcpServers": {    "catchhook": {      "serverUrl": "https://catchhook.app/mcp",      "headers": {        "Authorization": "Bearer YOUR_TOKEN"      }    }  }}

Start Debugging

Ask your AI assistant: "List my Catchhook endpoints" or "Wait for the next Stripe webhook on endpoint ep_abc123".

Available Tools

list_endpointsList all webhook endpoints

get_endpointGet endpoint details with setup checks

create_endpointCreate a new endpoint

delete_endpointDelete an endpoint

list_requestsList requests with provider-aware filtering

get_requestGet full request details

delete_requestDelete a request

delete_all_requestsBulk delete requests

wait_for_requestWait for a new webhook to arrive

send_test_requestSend a test webhook

replay_requestReplay a request with safety warnings

list_forwarding_targetsList forwarding targets

create_forwarding_targetCreate a forwarding target

delete_forwarding_targetDelete a forwarding target

diagnose_requestFull debugging analysis

compare_requestsProvider-aware diff between requests

get_endpoint_metricsEndpoint statistics

list_alertsList configured alerts

create_alertCreate a new alert

Common Questions

Which AI editors are supported?

Any MCP-compatible client: Claude Code, Cursor, Windsurf, Codex CLI, and others. We use the Streamable HTTP transport.

Is my data sent to third-party AI?

The MCP server returns your webhook data directly to your editor's AI assistant via your API token. Data handling depends on your editor's privacy settings—check your editor's documentation for details on how it processes tool responses.

What about OAuth support?

Bearer token auth is available now. OAuth 2.0 with dynamic client registration is coming soon.

Can I use this with my existing API token?

Yes. The same API tokens used for the REST API work with the MCP server. Create one in Account Settings.

Explore More Capabilities

Real-time Inspection

See every request as it arrives.

Replay & Forwarding

Re-send captured requests to any target.

AI Debugging

AI-powered webhook analysis.

Debug Webhooks Without Leaving Your Editor

Let your AI assistant inspect, diagnose, and replay webhooks while you focus on code.