A trust and control layer for proxying traffic to MCP servers
Gain control and visibility over AI agent infrastructure with AI Gateway-driven MCP capabilitiesBring MCP servers to production securely with Kong AI Gateway
AI agents are rapidly becoming core components of modern software, driving the need for structured, reliable interfaces to access tools and data. The Model Context Protocol (MCP) addresses this by enabling agents to reason, plan, and act across services. However, scaling MCP in remote, distributed environments introduces new operational challenges.
Kong AI Gateway enables teams to manage remote MCP traffic with enterprise-grade security, performance, authentication, context propagation, load balancing, and observability.
Learn how to:
MCP server options
Kong AI Gateway lets you either connect any external MCP server or autogenerate MCP tools from your APIs. Both approaches can be combined to integrate APIs and workflows into MCP-driven AI assistants while maintaining security, observability, and traffic control.
Use any external MCP server
For production environments, you can expose any remote MCP server to AI Gateway. This setup gives AI clients access to internal systems while enforcing strict control at the edge.
Use Kong AI Gateway plugins to:
- Secure access with plugins like OpenID Connect or Key Auth.
- Govern usage through rate limiting and traffic shaping.
- Enforce quotas based on tokens or user-level constraints.
- Monitor behavior using logging and distributed tracing with OpenTelemetry.
Expose any API as a secure MCP server
With Kong AI Gateway, you can also expose any API as an MCP server, auto-generate tools from its schema, and enforce OAuth-based access at the edge.
Use them to:
- Turn any API into an MCP server without writing custom code.
- Secure MCP endpoints with OAuth while keeping consistent access policies.
- Apply rate limiting, logging, and monitoring to MCP traffic.
- Integrate your APIs directly into MCP workflows and AI assistants.
Secure and govern your MCP traffic
Follow the tutorials below to learn how to secure, govern, and observe your MCP traffic using Kong AI Gateway.
Autogenerate secure MCP servers and tools
Explore guides and examples to auto-generate MCP servers and tools without custom code.
Kong also provides a built-in MCP server that connects directly to your Kong Konnect Control Planes. It offers read-only tools for analytics, configuration inspection, and Control Plane metadata—ideal for AI-driven workflows with Claude or other compatible assistants.
With Kong Konnect MCP server, you can use natural language to:
- Query API traffic across gateways with filters and time windows.
- List and inspect Services, Routes, Consumers, and plugins.
- Explore Control Plane hierarchies and group relationships.
- Build and test workflows without a production setup.
MCP traffic observability
Kong AI Gateway records detailed Model Context Protocol (MCP) traffic data so you can analyze how requests are processed and resolved.
- Logs capture session IDs, JSON-RPC method calls, payloads, latencies, and errors.
- Metrics track latency, response sizes, and error counts over time, giving you a complete view of MCP server performance and behavior.