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

Q: How do I add the Kong (AI API Gateway) MCP Server to Claude Code?

Run claude mcp add --transport http kong-ai-api-gateway-mcp -- in your terminal. Use claude mcp list to verify that all gateway management tools are correctly loaded.

Q: Can I automate LLM proxy setups with Kong (AI API Gateway) and Claude Code?

Yes, you can command Claude Code to run createservice and createaiplugin to set up your LLM proxy. This allows you to build headless deployment scripts for your AI services.

Q: How do I manage consumer keys using Kong (AI API Gateway) in Claude Code?

You can instruct the CLI agent to run createconsumerkey to generate API credentials. This lets you provision access keys for new clients directly from your terminal workspace.

Q: How do I clean up unused plugins from the command line?

Have the agent run deleteplugin with the target plugin ID to remove it from your gateway. This instantly strips the middleware from your service or route.

Manage your Kong (AI API Gateway) infrastructure from the terminal using the Claude Code CLI.

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 Claude Code

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Script Backend Service Registration

The `create_service` tool registers upstream service targets into your Kong gateway directly from your terminal session. Claude Code runs this command to declare your backend endpoints inside shell scripts or CI/CD pipelines. You get instant service provisioning without opening a browser. Following service creation, the agent executes `create_route` to bind public paths to the new upstream. This allows you to script complete environment setups from a single terminal prompt. It cuts out the manual configuration steps for your DevOps workflows.

Terminal-Driven AI Routing

The `create_ai_plugin` tool configures the `ai-proxy` plugin to manage LLM routing and hide provider keys. Claude Code uses this to quickly spin up secure gateways for your model deployments. It is ideal for SREs who need to provision AI endpoints from the command line. If an upstream model goes down or needs tuning, Claude Code calls `update_plugin` to swap providers or adjust rate limits. You can run these updates interactively or drop them into automated cron jobs. This keeps your AI infrastructure adaptive and secure.

Audit Gateway State in Claude Code

The `list_services` tool outputs all active backend services registered in your gateway. Claude Code uses this to verify the state of your infrastructure before applying updates or running migrations. It gives you raw, accurate data directly in your shell. To get a complete map of your active configuration, the agent combines this with `list_routes` and `list_plugins`. This outputs your entire routing topology and active security middleware. You can easily pipe this output to other CLI utilities for deep inspection.

Setup guide

Set up Kong (AI API Gateway) MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see kong-ai-api-gateway-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Kong (AI API Gateway) transactions." It will automatically discover and invoke the available Kong (AI API Gateway) tools.

Terminal

claude mcp add --transport http kong-ai-api-gateway-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Kong (AI API Gateway) MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "kong-ai-api-gateway-mcp": {
      "type": "url",
      "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 Claude Code

Run `claude mcp add --transport http kong-ai-api-gateway-mcp -- ` in your terminal. Use `claude mcp list` to verify that all gateway management tools are correctly loaded.

Yes, you can command Claude Code to run create_service and create_ai_plugin to set up your LLM proxy. This allows you to build headless deployment scripts for your AI services.

You can instruct the CLI agent to run create_consumer_key to generate API credentials. This lets you provision access keys for new clients directly from your terminal workspace.

Have the agent run delete_plugin with the target plugin ID to remove it from your gateway. This instantly strips the middleware from your service or route.

This server handles your Kong configuration data and consumer credentials strictly inside an ephemeral, zero-trust V8 sandbox. No sensitive gateway details or API keys are ever stored or exposed to external networks.

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