Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@UseWebhook MCP create a webhook endpoint to test my payment API"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Model Context Protocol (MCP) server for generating and inspecting webhooks
⚡ Generate webhook endpoints for testing
🔍 Inspect and diff HTTP request payloads
🔁 Replay requests from history
🔀 Forward requests to your localhost
⚡️ Powered by UseWebhook
Related MCP server: webhook-ai-mcp
Install usewebhook-mcp for Claude Desktop via Smithery:
npx -y @smithery/cli install @figstra/usewebhook-mcp --client claudeClone the repository:
git clone https://github.com/figstra/usewebhook-mcp.gitInstall dependencies:
cd usewebhook-mcp
npm installBuild the project:
npm run buildConfigure the server in your Claude MCP settings file:
{
"mcpServers": {
"usewebhook-mcp": {
"command": "node",
"args": ["path/to/your/usewebhook-mcp/build/index.js"],
"disabled": false,
"autoApprove": []
}
}
}# Install dependencies
npm install
# Start the development server
npm run devThis project is licensed under the MIT License. See the LICENSE file for details.
This server cannot be deployed
Receive, inspect, replay and deliver webhooks — with signature verification and agent triggers.
Keyless webhook endpoints: capture, wait, replay, forward, and generate types from real traffic.
A webhook inbox for agents: one call returns a live URL. Mock, verify, inspect and replay.
Instant no-signup webhook & HTTP-request inspector for testing webhooks and agent tool-callbacks.
