Use Kong with your AI.
Connect your account once and let the AI you already use work with it, without building another integration. Manage your API Gateway via Kong. orchestrate services, routes, and AI plugins directly from your agent.
Developed, maintained, and hosted by Vinkius.
MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED
Waiting for input…
Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.
Complete set · 10 capabilities
The complete Kong capability set.
These are the exact actions your AI can choose when you ask it to work with Kong.
01-04
4 capabilities in this set.
Part of 10 available through Kong.
- 01
Create consumer key
Generate an API Key credential for a Kong Consumer
- 02
Create route
Create a new Route to expose a Service in Kong
- 03
Create service
The payload must define the upstream URL, name, and protocol information. Create a new backend Service in Kong
- 04
Delete plugin
Delete and permanently remove a Plugin from the Kong Gateway
05-07
3 capabilities in this set.
Part of 10 available through Kong.
- 05
List consumers
List all Consumer profiles registered in Kong
- 06
List routes
List all routing rules configured in the Kong API Gateway
- 07
Create AI plugin
Frequently used for enabling the ai-proxy plugin for LLM routing and key encapsulation. Apply a new Plugin (like AI Proxy) to a specific Service
08-10
3 capabilities in this set.
Part of 10 available through Kong.
- 08
List plugins
G., Rate Limiting, AI Proxy, Key Auth) currently configured globally or scoped to specific Services/Routes. List all enabled Plugins on the Kong Gateway
- 09
List services
List all Services registered in the Kong API Gateway
- 10
Update plugin
Useful for adjusting rate limits dynamically or swapping AI model providers under heavy load. Update the configuration of an existing Kong Plugin
Observed, not estimated
871ms average. Fast in production.
Kong is checked daily against the live service.
- Fastest day
- 713ms
- Slowest day
- 1075ms
- 14-day trend
- Stable+2%
Connect your client
One URL. Every client.
Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.
Preview access · not provider authentication
The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Kong, so you can see the experience inside your AI.
It does not authenticate your account with Kong. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
Kong Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_v0JAMPJEymFJeA5BOdGXfYEBh1b3USJtcGdqANfK/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Kong capabilities are ready to use.
{
"mcpServers": {
"kong-ai-api-gateway-mcp": {
"url": "https://edge.vinkius.com/vk_preview_v0JAMPJEymFJeA5BOdGXfYEBh1b3USJtcGdqANfK/mcp"
}
}
}
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Step-by-step instructions for each client are in the guide. How to connect
FAQ
Questions Kong owners ask.
- 01
Can I use this server to manage Kong's AI Proxy plugin?
Absolutely. The create_ai_plugin capability 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.
- 02
How do I create a new API route through a conversation?
Use the create_route capability 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.
- 03
Can my agent generate new API keys for consumers?
Yes. The create_consumer_key capability allows you to provision new credentials for specific Consumers. This is perfect for onboarding new tenants or rotating keys for downstream applications securely.
Explore
More in Friends
LiteLLM (LLM Proxy & Spend Tracking) AI Connector
Manage your LLM gateway via LiteLLM — generate API keys, track spending, and orchestrate model fallback paths.
ViewLangGraph Cloud (Stateful AI Agents) AI Connector
Orchestrate stateful AI agents via LangGraph Cloud — manage assistants, monitor conversation threads, and hand
ViewRetell AI AI Connector
Empower your conversational AI to orchestrate, analyze, and automate phone calls or web-based voice agent inte
ViewOpen WebUI AI Connector
Manage your Open WebUI instance — list models, handle chat completions, and manage RAG collections directly fr
View
Suggestions
Bland AI AI Connector
Deploy AI phone agents that handle inbound and outbound calls with natural conversation for sales and customer
ViewAskHandle AI Connector
Manage AI chat rooms, capture leads, and automate messaging workflows directly through AskHandle.
ViewBland AI AI Connector
Deploy AI phone agents that handle inbound and outbound calls with natural conversation for sales and customer
ViewGradient AI (LLM API & Finetuning) AI Connector
Access powerful LLMs, fine-tune models on your own data, and generate embeddings directly through your AI agen
View
