How to Use the Kong (AI API Gateway) MCP in VS Code Copilot

Q: How do we enable the Kong (AI API Gateway) tools for our entire team in VS Code Copilot?

A team lead or admin should create a .vscode/mcp.json file in the project's root. After adding the Kong MCP Server details to that file, commit it to your Git repository. Every developer who pulls that change will have the tools enabled in Copilot.

Q: What information does Copilot need to create a new service with this Kong (AI API Gateway) tool?

To use createservice, you need to provide the name of the service and the upstream URL it should point to. For example: '@agent create a Kong service named user-api that points to http://user-service.internal:8080'.

Q: Is this just a wrapper around the Kong Admin API?

Yes, but the value is in the context. Your agent can createroute and then immediately help you write the application code that uses that route, all within the editor. It integrates infrastructure management directly into the development workflow.

Let your whole team manage Kong from VS Code Copilot. Standardize gateway operations with a shared config.

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 VS Code Copilot

Create your Vinkius account to connect Kong (AI API Gateway) to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Team-Wide Kong Management via Git

This MCP server lets you put your Kong gateway controls under source control. By adding the configuration to a `.vscode/mcp.json` file and committing it to your repo, everyone on the team gets the same tools in Copilot automatically. Now, any developer can ask Copilot to `create_service` for a new microservice or `create_route` to expose it. This standardizes how your team interacts with the gateway, removing the need for everyone to learn the Kong Admin API.

Secure and Configure AI Endpoints

Use Copilot to orchestrate Kong's powerful AI plugins. You can have it run `create_ai_plugin` to instantly add request transformations, caching, or rate-limiting to any LLM service. It's a simple way to enforce standards across all AI-powered features. Securing these endpoints is just as easy. Tell your agent to `create_consumer_key` to provision a new API key for a client application. Copilot can then help you integrate that key into your team's deployment process, ensuring nothing goes live without proper authentication.

Audit and Maintain Your Gateway from VS Code

Get a real-time view of your gateway's health without opening another tool. Ask Copilot to `list_plugins` or `list_services` to get an immediate inventory of what's deployed. This is perfect for quick checks during code reviews or debugging sessions. If a configuration needs to be changed, you can do it right there. Have your agent `update_plugin` to tweak a rate limit or `delete_plugin` to remove a deprecated feature. It turns VS Code into a reliable control plane for your entire API infrastructure.

Setup guide

Set up Kong (AI API Gateway) MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Kong (AI API Gateway) MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Kong (AI API Gateway) tools listed. Try asking: "List my recent Kong (AI API Gateway) transactions" and Copilot will invoke them automatically.

.vscode/mcp.json

{
  "mcpServers": {
    "kong-ai-api-gateway-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 VS Code Copilot

A team lead or admin should create a `.vscode/mcp.json` file in the project's root. After adding the Kong MCP Server details to that file, commit it to your Git repository. Every developer who pulls that change will have the tools enabled in Copilot.

Yes. The connection is handled by Vinkius, which provides a secure, ephemeral proxy for each command. You can use repository branch rules and code review to control who can commit changes to the `mcp.json` file that points to your production gateway.

To use `create_service`, you need to provide the name of the service and the upstream URL it should point to. For example: '@agent create a Kong service named `user-api` that points to `http://user-service.internal:8080`'.

Yes, but the value is in the context. Your agent can `create_route` and then immediately help you write the application code that uses that route, all within the editor. It integrates infrastructure management directly into the development workflow.

Your configuration data, like upstream URLs and consumer keys, is handled within a strict, single-tenant execution environment for each API call. The data is never written to disk or logged by Vinkius. It's passed directly to the Kong Admin API and then purged.

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