How to Use the Kong Gateway MCP in LangChain

Q: How do I use LangChain to add a route to an existing service in Kong Gateway?

Your agent first needs the service ID, which it gets using getservice. Then, it passes that ID into the createroute tool along with the desired path. The two steps are linked in a single chain.

Q: Can I manage Kong Gateway plugins with LangChain agents?

Yes. You have tools to createplugin, getplugin, listplugins, and updateplugin. An agent can find all plugins attached to a service and then update their configurations one by one.

Q: Is it possible to script a full service deployment in Kong Gateway with LangChain?

Absolutely. A single agent can execute a sequence: createservice, createroute, and then createplugin to attach middleware. It’s a complete, automated workflow for your Kong Gateway setup.

Manage Kong Gateway with composable LangChain agents. Chain commands to create services, add routes, and apply plugins in a single run.

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 LangChain

Create your Vinkius account to connect Kong Gateway to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Gateway Automation Pipelines

Connect Kong Gateway tools into logical sequences. Your agent can call `create_service` to register a new API, grab the new service ID, and immediately use it to call `create_route`, mapping a public path to it. No manual steps. This isn't just for one-off commands. You build chains that check for problems—like using `list_targets` to find unhealthy upstreams—and then automatically run `delete_target` to remove them from rotation. It's GitOps logic, but it runs in real time.

Full Observability with LangChain

Every MCP tool call is traced. You see exactly what your agent asked of the Kong Gateway, what the inputs were for `update_plugin`, and what the API returned. It's all logged in LangSmith. This gives you a complete audit trail. You can debug why a chain failed or prove that a specific consumer was created with `create_consumer` at a precise time. You're not flying blind.

Manage the Full API Lifecycle

Go beyond just routes and services. Your agents can manage the entire stack, from creating consumers with `create_consumer` to securing endpoints with `create_certificate` and `create_sni`. You can build complex logic, like an agent that onboards a new partner by creating a consumer, attaching a specific rate-limiting plugin with `create_plugin`, and then reporting back the new consumer's ID.

Setup guide

Set up Kong Gateway MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Kong Gateway tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "kong-gateway-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Kong Gateway transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Your agent first needs the service ID, which it gets using `get_service`. Then, it passes that ID into the `create_route` tool along with the desired path. The two steps are linked in a single chain.

Yes. You have tools to `create_plugin`, `get_plugin`, `list_plugins`, and `update_plugin`. An agent can find all plugins attached to a service and then update their configurations one by one.

Absolutely. A single agent can execute a sequence: `create_service`, `create_route`, and then `create_plugin` to attach middleware. It’s a complete, automated workflow for your Kong Gateway setup.

It's not just about calling endpoints. The MCP standardizes the tool definitions, so your LangChain agent understands what each tool does, what inputs it needs, and how to interpret the output without custom parsers.

The server only handles your Kong Gateway configuration data—things like service definitions, route paths, consumer credentials, and plugin settings. This data is processed ephemerally within the secure Vinkius sandbox for each tool call your agent makes.

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