How to Use the Kong (AI API Gateway) MCP in Mastra AI

Q: How do I configure Kong (AI API Gateway) inside Mastra AI?

Install @mastra/mcp@latest and initialize new MCPClient(). Pass the Vinkius URL, call listTools(), and spread the Kong operations into your agent's toolset.

Q: Can Mastra AI automatically retry Kong (AI API Gateway) service creation?

Yes. If createservice times out due to network latency, the framework's built-in retry logic executes the tool again with exponential backoff.

Q: How do I require human approval for Kong (AI API Gateway) deletions in Mastra AI?

Enable requireToolApproval on your agent. When the workflow attempts to run deleteplugin, it pauses execution until an administrator manually approves the action.

Q: How do I manage consumer keys in an MCP workflow?

Your agent runs createconsumerkey to generate the credential. It then passes that output to the next step in your workflow, such as storing it in a secret manager or emailing the developer.

Build resilient API gateway provisioning workflows by connecting Kong to 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 Kong (AI API Gateway) MCP to Mastra AI

Create your Vinkius account to connect Kong (AI API Gateway) 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 Kong (AI API Gateway) with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Orchestrate Kong configurations via MCP Server

The `create_service` tool defines the upstream URL and protocol information for your backend. Mastra AI executes this as the first step in an infrastructure provisioning workflow, automatically retrying if the network drops. Once the service exists, the workflow branches. The agent calls `create_route` to expose the path, and if that succeeds, it proceeds to attach plugins. If it fails, Mastra rolls back the state or notifies an admin.

Automate AI proxy adjustments in Mastra AI

Managing LLM routing requires the `create_ai_plugin` tool to encapsulate provider keys and proxy logic. Your Mastra AI MCP client can detect upstream provider outages and automatically swap the proxy target. If a specific model starts throwing 429s, the agent triggers `update_plugin`. It adjusts the rate limits or shifts traffic, using Mastra's exponential backoff to ensure the gateway configuration applies correctly.

Audit and clean up stale configurations

A scheduled Mastra workflow uses `list_consumers` and `list_routes` to audit the gateway. The agent pulls all registered profiles and routing rules to check for inactive endpoints. When it finds an obsolete proxy rule, the agent executes `delete_plugin` to permanently remove it from Kong. You build the logic to require human approval before deletion, and the framework handles the execution.

Setup guide

Set up Kong (AI API Gateway) 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 Kong (AI API Gateway) 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: "kong-ai-api-gateway-mcp-client",
  servers: {
    "kong-ai-api-gateway-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Kong (AI API Gateway) 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 Kong. 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 Kong (AI API 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 Kong (AI API Gateway) MCP in Mastra AI

Install `@mastra/mcp@latest` and initialize `new MCPClient()`. Pass the Vinkius URL, call `listTools()`, and spread the Kong operations into your agent's toolset.

Yes. If `create_service` times out due to network latency, the framework's built-in retry logic executes the tool again with exponential backoff.

Enable `requireToolApproval` on your agent. When the workflow attempts to run `delete_plugin`, it pauses execution until an administrator manually approves the action.

Your agent runs `create_consumer_key` to generate the credential. It then passes that output to the next step in your workflow, such as storing it in a secret manager or emailing the developer.

The server processes infrastructure schemas, specifically upstream URLs, plugin configurations, and consumer profiles. It runs in a zero-trust V8 isolate, meaning your routing definitions are destroyed immediately after the workflow completes.

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