How to Use the Webhook.site MCP in Vercel AI SDK

Q: How do I check the payloads when using Webhook.site with Vercel AI SDK?

Run your workflow, then use getrequests to grab all captured data for that token. This lets you see the exact incoming payload, which is essential debugging step before trying to stream any response.

Q: Can I simulate API failures with Webhook.site when building a Vercel AI SDK app?

Absolutely. Use setresponse to force the webhook to return a 401 or 500 error, even if the real service is up. This lets you test how your streaming UI handles failure gracefully.

Q: If I change my API logic, how do I update it on Webhook.site with Vercel AI SDK?

You use updateaction or updateglobalvariable. You don't need to touch your client code; you just modify the definitions right on the MCP Server side.

See real-time, debuggable webhook payloads directly in your streaming UI using Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Webhook.site to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debug Incoming Webhooks with the MCP Server

The `get_requests` tool shows you every payload captured by a specific token. If your streamed output isn't matching expectations, grab the raw data here first. You can inspect HTTP requests to pinpoint exactly what the upstream service sent. This is crucial when building user-facing AI apps with Vercel AI SDK. Seeing the exact incoming request lets you validate that the prompt context or payload data your client relies on is correct before it hits your streaming logic.

Control Responses Using Webhook.site MCP Server

You can use `set_response` to dynamically set what a token returns for any given request. This lets you simulate different API conditions—like an authentication failure or a successful data fetch—without changing the source system. For your AI SDK project, this means testing edge cases. You don't have to mess with staging environments; you just tell Webhook.site what response to send back when `execute_action` is called.

Manage Custom Actions for the ai-sdk

The MCP Server exposes actions via `list_actions`, `create_action`, and `update_action`. You define custom business logic that your AI client can trigger. This keeps complex operations out of your main application code. This allows you to build specific, reusable steps for the Vercel AI SDK. For example, if an agent needs to format data before streaming it, you write that formatting step as a custom action and call it directly from `generateText`.

Setup guide

Set up Webhook.site MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Webhook.site tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Webhook.site transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Run your workflow, then use `get_requests` to grab all captured data for that token. This lets you see the exact incoming payload, which is essential debugging step before trying to stream any response.

Absolutely. Use `set_response` to force the webhook to return a 401 or 500 error, even if the real service is up. This lets you test how your streaming UI handles failure gracefully.

It processes raw HTTP payloads and token metadata. Specifically, the server captures request bodies and headers, allowing you to inspect the underlying data type that drives your streamed content.

You use `update_action` or `update_global_variable`. You don't need to touch your client code; you just modify the definitions right on the MCP Server side.

It captures request payloads, including headers and bodies. This lets you analyze the full context of every interaction your streaming application has with an external service.

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