How to Use the Webhook.site MCP in Mastra AI

Q: If my workflow fails in Mastra AI, how do I debug with Webhook.site?

Use getrequests to view all captured payloads for the token involved. This shows you the exact data that was passed into the failing step, which is usually where the problem lies.

Q: Can I test different retry scenarios with Webhook.site and Mastra AI?

Yes. By using setresponse, you can simulate a sequence of failures (e.g., 401, then 503) to ensure your exponential backoff logic in the workflow handles multiple distinct error types.

Q: How do I ensure my workflow is using the correct context via Webhook.site with Mastra AI?

You check listglobalvariables to confirm the current value of the variable. If it looks wrong, you know your preceding step failed to update the state correctly.

Validate complex workflow inputs and outputs for reliable multi-step processes using Mastra AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Webhook.site MCP to Mastra AI

Create your Vinkius account to connect Webhook.site to Mastra AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Webhook.site with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trace Failure Points with the MCP Server

The `get_requests` tool fetches all requests captured by a token. When your complex workflow fails—say, payment retries fail—you grab these requests to see exactly what payload was sent at that failure point. This is critical for Mastra AI. You can trace why the second retry attempt failed versus the first one. Seeing the raw request data lets you fix the logic without rerunning costly processes.

Test Workflow Branches with Webhook.site MCP Server

Use `set_response` to define custom responses for specific tokens and requests. This means when your workflow hits a conditional branch, you can force it down the 'failure' path or the 'success' path. You test failure handling without needing live data. If the payment gateway usually succeeds but you suspect an edge case, you tell Webhook.site to return a specific error code instead.

Define Variables for Mastra AI Workflows

You manage state using `create_global_variable`, `update_global_variable`, and related list tools. This lets you define variables that carry context across multiple steps in your workflow engine. Instead of passing data through five different function calls, you store key pieces of information—like a unique transaction ID or an admin notification flag—in a global variable and let the entire Mastra AI system access it.

Setup guide

Set up Webhook.site MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Webhook.site tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "webhooksite-mcp-client",
  servers: {
    "webhooksite-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Webhook.site Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Webhook.site tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Webhook.site transactions"
);
console.log(result.text);

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Webhook.site. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Webhook.site now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Webhook.site MCP in Mastra AI

Use `get_requests` to view all captured payloads for the token involved. This shows you the exact data that was passed into the failing step, which is usually where the problem lies.

Yes. By using `set_response`, you can simulate a sequence of failures (e.g., 401, then 503) to ensure your exponential backoff logic in the workflow handles multiple distinct error types.

It processes request payloads and global variable definitions. You can inspect both the input data that triggers a step and any state variables passed between those steps.

You check `list_global_variables` to confirm the current value of the variable. If it looks wrong, you know your preceding step failed to update the state correctly.

It captures request payloads and global variable updates. This gives you a full audit trail of both the external inputs and the internal state changes that occurred during the multi-step run.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript