Kong API Gateway MCP for AI. Orchestrate services and routes from your agent.

Q: How do I check which services are available using listservices?

Running listservices shows every backend service registered in the gateway. This is your starting point for knowing what APIs you can actually route traffic to.

Q: What's the difference between createservice and createroute?

createservice defines the actual target endpoint (the 'what'). createroute defines how clients access it (the 'how'), mapping a URL to that service.

Q: How do I control AI plugins using createaiplugin?

You use createaiplugin when you need to enable the AI Proxy plugin on a specific backend service. This is how your gateway starts managing LLM traffic.

Q: What if I want to delete an unused module? Should I use deleteplugin?

Yes, deleteplugin permanently removes the specified plugin from the gateway configuration. Use this when you know a module is obsolete and needs removal.

Q: Can I generate API keys for existing users using createconsumerkey?

Absolutely. First, use listconsumers to find the user profile name, then use createconsumerkey to issue a brand new credential set for that consumer.

Q: How do I adjust rate limiting or change an LLM provider using updateplugin?

You use updateplugin to modify existing configurations in real time. This lets you adjust things like rate limits or swap out AI model providers instantly, which is crucial when your traffic needs change suddenly.

Q: What information does listconsumers give me about our platform's users?

Running listconsumers provides a roster of every consumer profile registered in Kong. This helps engineers audit which teams or applications are using the gateway and verify their credentials before troubleshooting access issues.

Q: What specific details can listservices provide about backend dependencies?

The output from listservices shows the core definition for each upstream target. This includes the required URL, name, and communication protocol, helping developers map out live backend services before configuring routes.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

Kong API Gateway MCP lets your agent control the full lifecycle of services, routes, and plugins. You can define backend services, map traffic flows, apply AI proxies for LLM routing, and generate consumer keys—all without touching a dashboard.

What your AI can do

List consumers

Retrieves a list of all registered consumer profiles managed by Kong.

Create consumer key

Generates an API key credential for a consumer profile in the gateway.

Create ai plugin

Applies a new Plugin, such as AI Proxy, to a specific backend service.

+ 7 more capabilities included

Define Backend Services

Creates new upstream definitions for services, specifying the required URL and communication protocol.

Map Client Endpoints

Configures inbound routing rules, telling the gateway how to direct client requests based on paths or hostnames.

Manage API Authentication

Lists consumer profiles and generates new API keys for tracking specific user access.

Configure AI Proxies

Applies and adjusts the ai-proxy plugin to control LLM routing, model providers, and key encapsulation settings.

Audit Gateway Plugins

Lists all active plugins (like Rate Limiting or AI Proxy) across the gateway, allowing you to remove unused modules instantly.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Kong (AI API Gateway) - 10 Tools

These tools give you direct command access to manage every piece of your API gateway, from defining backends to controlling AI traffic.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using Kong (AI API Gateway) on Vinkius

List Consumers

Retrieves a list of all registered consumer profiles managed by Kong.

Create Consumer Key

Generates an API key credential for a consumer profile in the gateway.

Create Ai Plugin

Applies a new Plugin, such as AI Proxy, to a specific backend service.

Create Route

Establishes a new routing rule to expose a defined backend service through a...

Create Service

Defines a brand new, upstream backend service, including its full URL and...

Delete Plugin

Permanently removes an existing plugin configuration from the gateway.

List Plugins

Lists every enabled plugin, such as Rate Limiting or AI Proxy, configured across the gateway.

List Routes

Retrieves all currently active routing rules defined in the Kong API Gateway.

List Services

Retrieves a list of every backend service registered and managed by the gateway.

Update Plugin

Modifies the configuration of an existing plugin, allowing dynamic adjustments to...

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The Kong API Gateway integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

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

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the Kong API Gateway tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

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

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with Kong (AI API Gateway), then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,100+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

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.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 10 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

The Pain of API Management in Dedicated UIs

Right now, managing an API gateway means context switching. You log into the Kong Manager UI to check routes; you jump to a CLI session to audit plugins; and if you need to change rates, you copy-paste values across three different tabs. It's tedious, slow, and prone to human error.

With this MCP, it’s conversational. Tell your agent what needs fixing—for example, 'I need the payments API accessible via `/v2/payments`.' The agent handles the sequence: checking if `create_service` is needed, then executing the `create_route`. You get the result without leaving your chat window.

Managing Your Gateway with Kong (AI API Gateway)

You no longer have to manually navigate complex forms just to update a setting. For instance, instead of finding the specific plugin settings and then updating them, you simply ask the agent to adjust rate limits using `update_plugin`. Or if an old service is abandoned, running `delete_plugin` instantly cleans up that module.

The difference is simple: it moves infrastructure governance from a multi-step GUI process into a single, verifiable conversation. It’s direct control.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

This connector gives you direct command over your Kong API Gateway instance. Instead of logging into a management UI or running complex CLI commands, your agent handles the entire process via natural language conversation. You can discover all existing services; list every enabled plugin to check for unused modules; and define entirely new backend services by specifying their URL and protocol.

Need to expose that service? Simply create a route mapping specific paths or hosts to it. It's also where you manage access: generate API keys for consumers, configure rate limits by updating plugins, or apply the ai-proxy plugin to handle LLM traffic routing. If your workflow needs this level of infrastructure control, connecting via Vinkius is the fastest way to get started.

Built · Hosted · Managed by Vinkius Kong API Gateway MCP - Orchestrate Services & Routes

Server ID 019d75c2-99c6-7031-8d39-cbb0ae3d2677

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

Who is this actually for?

Platform Engineers who dread context switching between the CLI and a web UI. Backend Developers needing to spin up new endpoints without leaving their terminal. AI Ops Teams managing complex LLM traffic flow.

DevOps Engineer

Uses this MCP to audit enabled plugins, delete unused modules, and define global gateway configurations via chat.

Backend Developer

Creates new services with specific upstream URLs or sets up routes so that a newly built microservice is immediately accessible.

AI Operations Specialist

Adjusts the ai-proxy plugin configuration in real time, swapping out AI models or changing rate limits to manage costs and performance.

What Changes When You Connect

You stop context switching. Instead of navigating between the CLI, a web UI, and documentation, you talk to your agent to define services or update plugins.

Manage access control granularly. Use list_consumers followed by create_consumer_key to instantly issue credentials for any specific client or tenant.

Control AI traffic flow dynamically. With the ability to update_plugin, you can swap out LLM models or adjust rate limits on the fly, optimizing provider costs without downtime.

Build services quickly. The combination of create_service and create_route lets you define a full microservice endpoint from scratch in two steps.

Keep your gateway clean. Run list_plugins to audit what's running; then use delete_plugin to remove outdated modules, keeping the pipeline streamlined.

See it in action

01 01

A new backend needs an endpoint.

The developer runs into a dead end trying to expose their service. They ask the agent: 'Set up my inventory API.' The agent first calls create_service with the upstream URL, then uses create_route to map the appropriate path, making it live instantly.

02 02

The AI model provider changed.

The Ops team finds that OpenAI's rate limits are too low. They instruct their agent: 'Increase the limit and switch models.' The agent uses update_plugin to adjust the Rate Limiting settings on the existing plugin, avoiding a manual configuration patch.

03 03

We need to track usage for a new partner.

The security team needs dedicated access control. They ask the agent to list all current consumers using list_consumers, identify the partner's account, and then use create_consumer_key to generate a unique credential set.

04 04

The gateway is bloated.

A Platform Engineer wants to audit the entire infrastructure. They run list_plugins to see what's active, spot an old module, and immediately use delete_plugin to clean up the proxy pipeline.

The honest tradeoffs

Bypassing API calls for debugging.

Anti-pattern

A developer tries to manually edit a route definition directly in the Kong Manager UI, risking partial configuration updates that leave services in an unknown state.

The Fix

Always use the agent. If you need to change a service path or update a plugin config, tell the agent to update_plugin or create_route. The MCP handles transactional integrity.

Assuming services are already defined.

Anti-pattern

The developer assumes that because they know the URL for the inventory API, it's available. They try to create a route without first calling create_service to define the backend.

The Fix

First, always call list_services or instruct the agent to use create_service with the full upstream details. You can't route traffic until the target service exists.

Ignoring existing access credentials.

Anti-pattern

The team spins up a new client and immediately asks for a key, forgetting that other consumers exist on the gateway. They only address one user at a time.

The Fix

Start by running list_consumers. This provides an immediate overview of all tenants; then you can use create_consumer_key to manage specific credentials.

When It Fits, When It Doesn't

Use this MCP if your job involves managing the API lifecycle, meaning defining services, routing traffic, and adjusting plugins. It’s for people who live in infrastructure code—the Platform Engineers and Backend Developers. Don't use it if you just need to read logs or view general usage statistics; those are separate tools. You should use list_services and list_routes when you only need visibility, but if you need to change something—whether that’s setting up a route via create_route, modifying rate limits with update_plugin, or granting access with create_consumer_key—this MCP is your primary interface.

Questions you might have

How do I check which services are available using list_services? +

Running list_services shows every backend service registered in the gateway. This is your starting point for knowing what APIs you can actually route traffic to.

What's the difference between create_service and create_route? +

create_service defines the actual target endpoint (the 'what'). create_route defines how clients access it (the 'how'), mapping a URL to that service.

How do I control AI plugins using create_ai_plugin? +

You use create_ai_plugin when you need to enable the AI Proxy plugin on a specific backend service. This is how your gateway starts managing LLM traffic.

What if I want to delete an unused module? Should I use delete_plugin? +

Yes, delete_plugin permanently removes the specified plugin from the gateway configuration. Use this when you know a module is obsolete and needs removal.

Can I generate API keys for existing users using create_consumer_key? +

Absolutely. First, use list_consumers to find the user profile name, then use create_consumer_key to issue a brand new credential set for that consumer.

How do I adjust rate limiting or change an LLM provider using update_plugin? +

You use update_plugin to modify existing configurations in real time. This lets you adjust things like rate limits or swap out AI model providers instantly, which is crucial when your traffic needs change suddenly.

What information does list_consumers give me about our platform's users? +

Running list_consumers provides a roster of every consumer profile registered in Kong. This helps engineers audit which teams or applications are using the gateway and verify their credentials before troubleshooting access issues.

What specific details can list_services provide about backend dependencies? +

The output from list_services shows the core definition for each upstream target. This includes the required URL, name, and communication protocol, helping developers map out live backend services before configuring routes.

Can I use this server to manage Kong's AI Proxy plugin? +

Absolutely. The create_ai_plugin tool is specifically designed to inject the ai-proxy plugin onto Services. You can define providers like OpenAI or Anthropic and manage model routing directly through your agent.

How do I create a new API route through a conversation? +

Use the create_route tool and provide a JSON payload defining the paths and the Service ID it should point to. Your agent will handle the Admin API call to provision the routing rule instantly.

Can my agent generate new API keys for consumers? +

Yes. The create_consumer_key tool allows you to provision new credentials for specific Consumers. This is perfect for onboarding new tenants or rotating keys for downstream applications securely.

Connect to your AI in seconds.

List consumers

Create consumer key

Create ai plugin

Kong (AI API Gateway) - 10 Tools

Make your AI actually useful.

List Consumers

Create Consumer Key

Create Ai Plugin

Create Route

Create Service

Delete Plugin

List Plugins

List Routes

List Services

Update Plugin

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

The Pain of API Management in Dedicated UIs

Managing Your Gateway with Kong (AI API Gateway)

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

A new backend needs an endpoint.

The AI model provider changed.

We need to track usage for a new partner.

The gateway is bloated.

The honest tradeoffs

Bypassing API calls for debugging.

Assuming services are already defined.

Ignoring existing access credentials.

When It Fits, When It Doesn't

Questions you might have