How to Use the Hookdeck MCP in Mastra AI

Q: How do I add Hookdeck tools to a Mastra AI agent?

Instantiate new MCPClient with your Vinkius server URL, retrieve the tools via mcpClient.listTools(), and spread them into your agent's tools array. The client automatically configures the correct HTTP or SSE transport.

Q: Can Mastra AI automatically retry a failed Hookdeck event?

Yes, your agent can catch delivery errors and call retryevent to replay the payload. You can combine this with Mastra's native workflow retry policies to handle transient network blips gracefully.

Q: How do I manage Hookdeck connection state transitions in Mastra AI?

Use getconnection to check the current routing state, then use disableconnection or enableconnection inside your conditional workflow steps. This allows your agents to dynamically route traffic based on live system health.

Build self-healing webhook workflows in Mastra AI by connecting Hookdeck routing and automated retry tools via 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 Mastra AI

Create your Vinkius account to connect Hookdeck 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 Hookdeck with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated incident response with Mastra AI workflow steps.

`get_metrics_attempts` lets your Mastra AI agents continuously monitor Hookdeck delivery failure rates across all active endpoints. When failures spike past your threshold, the Mastra workflow engine triggers conditional branches to isolate the broken Hookdeck endpoint. The Mastra agent then calls `pause_connection` to stop sending traffic to the failing Hookdeck server. Mastra AI's built-in retry mechanics hold the state until downstream services recover, preventing database locks and lost payloads.

Multi-step transformation deployments using Mastra AI.

`create_transformation` inserts custom Javascript payload parsing directly into your Hookdeck routing pipeline via a Mastra AI agent. The Mastra agent writes the code, tests it, and deploys it to Hookdeck in a single workflow run. If you need to update existing Hookdeck routing rules, the Mastra agent calls `update_transformation` and runs verification tests. This automated Mastra workflow ensures your payload shapes match downstream API changes without manual intervention.

Human-in-the-loop approvals for Hookdeck MCP Server actions.

`delete_connection` requires strict guardrails because dropping a Hookdeck webhook source can break production integrations. Mastra AI's `requireToolApproval` interceptor halts the agent before it executes this destructive Hookdeck action. The Mastra workflow pauses and alerts an engineer in Slack, requesting confirmation to proceed with the Hookdeck connection removal. Once approved, the agent invokes `delete_connection` and cleans up the associated Hookdeck resources without manual terminal commands.

Setup guide

Set up Hookdeck 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 Hookdeck 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: "hookdeck-mcp-client",
  servers: {
    "hookdeck-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Hookdeck 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 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 Mastra AI

Instantiate `new MCPClient` with your Vinkius server URL, retrieve the tools via `mcpClient.listTools()`, and spread them into your agent's tools array. The client automatically configures the correct HTTP or SSE transport.

Yes, your agent can catch delivery errors and call `retry_event` to replay the payload. You can combine this with Mastra's native workflow retry policies to handle transient network blips gracefully.

Use `get_connection` to check the current routing state, then use `disable_connection` or `enable_connection` inside your conditional workflow steps. This allows your agents to dynamically route traffic based on live system health.

Yes, your agent can call the list endpoint with filters to find specific failing webhooks. It can then parse the returned array and loop through individual events to trigger targeted retries.

All communication runs through Vinkius's zero-trust V8 isolates, securing your routing configurations. The server only accesses Hookdeck endpoints using ephemeral tokens, meaning your master API keys are never exposed to the LLM or stored in workflow logs.

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