How to Use the Hookdeck (Webhook Gateway) MCP in Vercel AI SDK

Q: How do I set up the Hookdeck (Webhook Gateway) MCP Server in Vercel AI SDK?

Install @ai-sdk/mcp and ai. Configure your connection using createMCPClient with your Vinkius HTTP endpoint, then pass the tools from mcpClient.tools() into generateText or streamText.

Q: Can my Vercel AI SDK agent handle Hookdeck (Webhook Gateway) bulk retries?

Yes. Your agent can run bulkretryevents based on specific error queries to handle large-scale recovery. The Vercel AI SDK streams the status of the bulk operation back to your UI in real-time.

Q: How secure is my webhook payload data when using this integration?

Your raw webhook headers and body payloads retrieved via geteventraw only pass through Vinkius's ephemeral, zero-trust sandbox. No webhook payload data is stored permanently on our servers, keeping your sensitive transaction records secure.

Pipe live webhook delivery metrics and connection controls straight into your Next.js frontend with the 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 Hookdeck (Webhook Gateway) MCP to Vercel AI SDK

Create your Vinkius account to connect Hookdeck (Webhook Gateway) 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 (Webhook Gateway) with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live Webhook Troubleshooting with Vercel AI SDK

Your AI client can now spot webhook failures and fix them live on your dashboard. When a customer reports a missing webhook, your agent uses `list_events` and `get_event_raw` to inspect the payload. The raw data streams directly to your React components, letting users see the exact failure reason without refreshing. If the issue was a temporary server blip, your agent invokes `retry_event` to push it through. You don't have to build custom API wrappers or loading spinners. The Vercel AI SDK handles the execution stream, updating the UI state the millisecond Hookdeck processes the retry.

Instant Traffic Control in Edge Functions

Pause or resume webhook traffic on the fly during database migrations or third-party outages. Your agent calls `pause_connection` when downstream services fail, putting incoming events on hold. This keeps your queue clean and prevents dropping critical webhook payloads when your database goes offline. Once the migration wraps up, your agent runs `unpause_connection` to safely resume the flow. Because the Vercel AI SDK is compatible with edge runtimes, these agent-driven traffic controls execute with minimal latency right from the edge.

Real-Time Queue Monitoring and Metrics

Build live-updating monitoring widgets that display Hookdeck queue depths and success rates. Your agent queries `get_metrics_queue_depth` and `get_metrics_events` to compile current performance data. It streams these metrics directly into your dashboard, giving your engineering team instant visibility into message backlogs. If a queue starts backing up, the agent can immediately alert your on-call team or trigger automated recovery steps. Using this MCP Server with your React frontend means you get instant system observability without polling databases or writing custom WebSockets.

Setup guide

Set up Hookdeck (Webhook Gateway) 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 (Webhook Gateway) 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 (Webhook Gateway) 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 (Webhook Gateway) 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 (Webhook Gateway) MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and `ai`. Configure your connection using `createMCPClient` with your Vinkius HTTP endpoint, then pass the tools from `mcpClient.tools()` into `generateText` or `streamText`.

Yes. Your agent can run `bulk_retry_events` based on specific error queries to handle large-scale recovery. The Vercel AI SDK streams the status of the bulk operation back to your UI in real-time.

Vinkius handles the underlying authentication and gateway limits. Your agent can safely run read operations like `list_connections` or write operations like `update_destination` without hitting raw Hookdeck API limits directly.

Yes, both Vinkius and the Vercel AI SDK are optimized for edge runtimes. This allows your agent to fetch raw payload data via `get_request_raw` and execute retries inside fast, serverless environments.

Your raw webhook headers and body payloads retrieved via `get_event_raw` only pass through Vinkius's ephemeral, zero-trust sandbox. No webhook payload data is stored permanently on our servers, keeping your sensitive transaction records secure.

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