Which AI coding agents support webhooks.cc?

The MCP server works with Claude Code, Cursor, VS Code (Copilot), OpenAI Codex, Windsurf, and Claude Desktop. Any tool that supports the Model Context Protocol can connect.

What can an AI agent do with webhooks.cc?

Your AI agent can create endpoints, send test webhooks, inspect captured requests, configure mock responses, and replay requests to localhost — all through natural language.

MCP Server

The @webhooks-cc/mcp package lets AI coding agents create endpoints, inspect webhooks, send test payloads, and replay captured requests — all through natural language.

Updated Mar 2026

Your API key

Paste your API key to fill it into every command below. It stays in your browser only — nothing is sent or stored.

Get your key from your account page.

One-click install

Add to Cursor

Paste your key above first — it gets baked into the install link.

Add to VS Code

VS Code prompts you for your key during install.

Claude Code

claude mcp add -s user webhooks-cc -e WHK_API_KEY=whcc_... -- npx -y @webhooks-cc/mcp

Cursor (CLI)

npx @webhooks-cc/mcp setup cursor --api-key whcc_...

VS Code (CLI)

npx @webhooks-cc/mcp setup vscode --api-key whcc_...

OpenAI Codex

codex mcp add webhooks-cc -e WHK_API_KEY=whcc_... -- npx -y @webhooks-cc/mcp

Windsurf

npx @webhooks-cc/mcp setup windsurf --api-key whcc_...

Claude Desktop

npx @webhooks-cc/mcp setup claude-desktop --api-key whcc_...

Manual config

For any tool that reads an MCP config JSON file:

{
  "mcpServers": {
    "webhooks-cc": {
      "command": "npx",
      "args": ["-y", "@webhooks-cc/mcp"],
      "env": {
        "WHK_API_KEY": "whcc_..."
      }
    }
  }
}

Available tools

The MCP server exposes 25 tools your AI agent can call:

For provider templates in send_webhook, secret is required. The MCP server does not inject a default secret.

Endpoint management

Tool	Description
`create_endpoint`	Create a new webhook endpoint
`list_endpoints`	List all your endpoints
`get_endpoint`	Get details for an endpoint by slug
`update_endpoint`	Update an endpoint name or mock response
`delete_endpoint`	Delete an endpoint and its requests
`create_endpoints`	Create multiple endpoints in one call (1-20)
`delete_endpoints`	Delete multiple endpoints in one call (1-100)

Sending and testing

Tool	Description
`send_webhook`	Send a test webhook (manual or provider template) to an endpoint
`send_to`	Send a signed webhook directly to any URL (localhost, staging, etc.)
`preview_webhook`	Preview a webhook request without sending it
`test_webhook_flow`	Run a full test flow: create, mock, send, wait, verify, replay, cleanup

Request management

Tool	Description
`list_requests`	List captured requests for an endpoint
`get_request`	Get full details of a captured request
`wait_for_request`	Wait for an incoming request (polling)
`wait_for_requests`	Wait for multiple incoming requests
`search_requests`	Search requests across endpoints with full-text search
`count_requests`	Count requests matching filters
`clear_requests`	Delete requests for an endpoint without deleting the endpoint

Request analysis

Tool	Description
`replay_request`	Replay a captured request to a target URL
`compare_requests`	Compare two requests and show structured differences
`extract_from_request`	Extract specific JSON fields from a request body
`verify_signature`	Verify the webhook signature on a captured request

Utilities

Tool	Description
`list_provider_templates`	List supported providers, templates, and signing metadata
`get_usage`	Check current request usage, quota, and plan
`describe`	Describe all available SDK operations

Prompts

The MCP server provides 3 prompt templates for common workflows:

debug_webhook_delivery — diagnose why webhook delivery is failing or missing
setup_provider_testing — set up webhook testing for a specific provider
compare_webhook_attempts — compare two webhook deliveries or retries

Resources

Three resources provide read-only access to your webhook data:

endpoints-overview (webhooks://endpoints) — all endpoints with recent activity
endpoint-recent-requests (webhooks://endpoint/{slug}/recent) — last 10 requests at an endpoint
request-details (webhooks://request/{id}) — full details of a specific request

Example conversation

With the MCP server connected, you can talk to your AI agent naturally:

You: "Create a webhook endpoint for testing Stripe"
Agent: Created endpoint "stripe-test" at https://go.webhooks.cc/w/abc123

You: "Set it to return 201 with {"received": true}"
Agent: Updated mock response for stripe-test

You: "Send a Stripe checkout.session.completed template webhook to stripe-test"
Agent: Sent signed Stripe template to stripe-test

You: "Show me what was captured"
Agent: 1 request captured:
  POST /w/abc123 — stripe-signature + checkout.session.completed payload

You: "Replay that to my local server"
Agent: Replayed to http://localhost:3000/webhooks — got 200 OK

Learn more

SDK Overview

The TypeScript SDK that powers the MCP server.

API Reference

All methods, matchers, and types.

Testing patterns

CI/CD integration examples.