How to Use the Hookdeck MCP in Vercel AI SDK

Q: How do I register the Hookdeck MCP Server tools with the Vercel AI SDK?

Call createMCPClient with your Vinkius HTTP URL, then pass mcpClient.tools() to streamText or generateText. Remember to run mcpClient.close() once the request completes to prevent socket leaks.

Q: How does Vercel AI SDK handle long-running Hookdeck bulk retries?

The agent uses listevents to find failed payloads and triggers retryrequest sequentially. Because the SDK streams tool execution states, your users see each retry status as it happens instead of waiting for a bulk timeout.

Pipe Hookdeck webhook metrics and routing status directly into your React or Next.js UI using the Vercel AI SDK and this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hookdeck MCP to Vercel AI SDK

Create your Vinkius account to connect Hookdeck 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 Hookdeck with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live webhook queue monitoring in your Vercel AI SDK app.

`get_metrics_queue_depth` is the tool your Vercel AI SDK agent calls to fetch current Hookdeck queue sizes when a user asks about webhook backlogs. Instead of waiting for a full page reload, the raw numbers stream straight into your React components as the tool executes. You see Hookdeck ingestion bottlenecks without polling your API inside Next.js. By combining this with `get_metrics_attempts`, your Vercel AI SDK interface displays live delivery rates and failure counts right when the agent pulls them.

Real-time connection pausing from the chat interface.

`pause_connection` gives your Vercel AI SDK agent the power to halt Hookdeck event routing immediately when a user flags an incident in your chat UI. The SDK handles this tool call on the edge, pausing the specified Hookdeck connection without spinning up a heavy serverless container. Once the downstream outage is resolved, the user tells the Vercel AI SDK agent to resume the Hookdeck flow. The agent invokes `unpause_connection` and streams the confirmation state back to the UI, showing the active connection status instantly.

Interactive transformation testing for developers.

`test_transformation` runs JavaScript payload mutations directly inside your Vercel AI SDK developer dashboard using this Hookdeck MCP Server. Your Next.js agent takes a sample payload, applies the code, and shows the modified Hookdeck output in real time. If the code needs adjustments, the developer edits it inline, and the Vercel AI SDK agent calls `update_transformation` to save the changes to Hookdeck. This feedback loop eliminates the need to jump back and forth between Hookdeck's console and your local terminal.

Setup guide

Set up Hookdeck 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 Hookdeck 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 Hookdeck 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 Hookdeck. 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 Hookdeck 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 Hookdeck MCP in Vercel AI SDK

Call `createMCPClient` with your Vinkius HTTP URL, then pass `mcpClient.tools()` to `streamText` or `generateText`. Remember to run `mcpClient.close()` once the request completes to prevent socket leaks.

Yes, the server runs on Vinkius's isolated infrastructure, allowing your edge functions to invoke `retry_event` with minimal latency. This keeps your edge bundle light because you don't package the Hookdeck SDK itself.

The agent uses `list_events` to find failed payloads and triggers `retry_request` sequentially. Because the SDK streams tool execution states, your users see each retry status as it happens instead of waiting for a bulk timeout.

Vinkius manages the authentication handshake for you, so your edge code only needs a single endpoint token. You don't have to store or rotate individual workspace keys in your local environment variables.

Hookdeck event payloads and connection metadata pass through ephemeral V8 isolates that destroy themselves after execution. No webhook bodies or secret tokens are written to persistent storage on the Vinkius platform.

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