How to Use the Kong Gateway MCP in LlamaIndex

Q: Can LlamaIndex help me find misconfigured routes in Kong Gateway?

Yes. You can create an agent that periodically runs listroutes and listservices, indexes the results, and then lets you query for anomalies, like routes pointing to a non-existent service ID.

Turn your Kong Gateway configuration into a searchable knowledge base with LlamaIndex. Ask your MCP agent questions, get answers from live API data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kong Gateway MCP to LlamaIndex

Create your Vinkius account to connect Kong Gateway to LlamaIndex 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 Gateway with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Your Gateway's State

This isn't just about running commands; it's about remembering the results. LlamaIndex can automatically index the output of tools like `list_services` and `list_routes` into a vector store. Now you can ask questions in natural language. 'Which services were created last week?' or 'Show me all routes that point to the `billing-api` upstream.' Your agent finds the answer from indexed, real-world data, not by guessing.

Build Configuration-Aware RAG

Combine your internal documentation with live gateway state. A query can pull markdown files explaining your rate-limiting policies and cross-reference them with the live output of `list_plugins`. Your agent gets the full picture. It knows both the 'why' from your docs and the 'what' from the Kong Gateway itself. This means better, more accurate answers when you're debugging an issue.

Query Your Kong Gateway MCP Server

Use the agent as an interactive shell for your gateway. Ask it to `get_status` or `get_info` to check on node health. Then, have it `list_consumers` to see who is connected. You don't need to remember exact tool names or parameters. LlamaIndex translates your natural language query into the right sequence of MCP tool calls, making ad-hoc exploration fast and easy.

Setup guide

Set up Kong Gateway MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Kong Gateway MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Kong Gateway tools.",
)
response = await agent.run("List recent Kong Gateway data")

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 Gateway. 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 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 Gateway MCP in LlamaIndex

Yes. You can create an agent that periodically runs `list_routes` and `list_services`, indexes the results, and then lets you query for anomalies, like routes pointing to a non-existent service ID.

You'd ask your LlamaIndex agent, 'List all active plugins.' It would use the `list_plugins` tool, index the output, and present you with a formatted list. You could then ask follow-up questions about specific plugin configurations.

That's the core use case. By indexing the output of tools like `list_services` and `list_routes`, you create a knowledge base that a RAG agent can use to answer questions from your team about the Kong Gateway configuration.

No. Vinkius manages the connection securely. You provide a single Vinkius endpoint token to your agent, and all authentication with the Kong Admin API is handled by the managed MCP server.

The server itself is stateless. It processes Kong Gateway configuration data—like upstream targets, service URLs, and route paths—and returns it to your LlamaIndex agent. It's your responsibility to secure the vector index where LlamaIndex stores this data.

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