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

Q: How do I configure Kong (AI API Gateway) in Pydantic AI?

Install pydantic-ai-slimmcp. Initialize an MCPToolset with your server's HTTP URL. Pass this toolset to your agent to automatically expose the Kong management capabilities.

Q: Why use Pydantic AI to manage Kong (AI API Gateway)?

It prevents silent failures. If listroutes returns a JSON structure that doesn't match your expected Pydantic model, the agent fails loudly instead of hallucinating a configuration state.

Q: Can I restrict rate limits on specific routes?

Your agent targets the exact path using listroutes and applies constraints via createaiplugin. This isolates the rate limit to a single endpoint without affecting global gateway traffic.

Type-safe API gateway management with Pydantic AI and Kong (AI API Gateway).

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 Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Route Provisioning

The `create_service` tool on your MCP Server defines your upstream LLM provider details. Your agent maps this service to a public path using `create_route`, creating a strict ingress point for your applications. Because Pydantic AI validates every response, the gateway configuration must match your predefined schemas. If the gateway returns an unexpected protocol format, the framework throws a validation error immediately.

Configure AI Plugins via MCP Server

Applying `create_ai_plugin` attaches proxy behavior to your newly created routes. This handles request transformation and credential injection before the traffic hits the provider. You adjust these settings dynamically with `update_plugin`. When traffic spikes, your agent modifies the rate limits or shifts the model provider, and Pydantic AI guarantees the payload structure is correct before execution.

Secure Consumer Access

Generating access tokens requires calling `create_consumer_key`. The agent provisions these credentials for specific users and securely returns them to your calling application. You audit active users by executing `list_consumers` and `list_plugins`. If the agent finds an unauthorized plugin or an expired consumer, it uses `delete_plugin` to strip the access rule from the gateway.

Setup guide

Set up Kong (AI API Gateway) MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

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

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Kong (AI API Gateway) tools.",
)

result = await agent.run("List recent Kong (AI API Gateway) transactions")
print(result.output)

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 Pydantic AI

Install `pydantic-ai-slim[mcp]`. Initialize an `MCPToolset` with your server's HTTP URL. Pass this toolset to your agent to automatically expose the Kong management capabilities.

It prevents silent failures. If `list_routes` returns a JSON structure that doesn't match your expected Pydantic model, the agent fails loudly instead of hallucinating a configuration state.

Your agent targets the exact path using `list_routes` and applies constraints via `create_ai_plugin`. This isolates the rate limit to a single endpoint without affecting global gateway traffic.

Pydantic AI intercepts the request before it ever reaches the MCP Server. It validates the `create_service` arguments against your schema and rejects the action if the protocol or URL is invalid.

The MCP Server processes routing rules, upstream URLs, and plugin schemas. Pydantic AI sends these strictly typed payloads over a secure connection. The hosting platform operates a zero-trust model, ensuring no configuration data persists in the proxy layer.

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