Kong AI Gateway — Plugin Catalog

Kong’s AI capabilities ship as a set of plugins on top of the core Kong Gateway/Konnect data plane, rather than a separate product. The first six AI plugins shipped in Kong Gateway 3.6 (Feb 2024) as open source; more advanced governance plugins were added later and require Kong Enterprise or Konnect licensing.

Traffic proxying & routing

PluginWhat it does
AI ProxyThe base plugin. Normalizes one request format across providers (OpenAI, Anthropic, Azure, Cohere, Bedrock, Gemini, etc.), translates it to the target’s native format, and transforms the response back. Open source.
AI Proxy AdvancedMulti-target version of AI Proxy — proxies to several providers/models at once and adds load balancing. This is what powers the failover setup we built earlier.
AI MCP ProxyFronts MCP servers (passthrough, conversion, or listener mode), covered in the registry/gateway duty above.
AI MCP OAuth2OAuth2 resource-server behavior specifically for MCP traffic.
AI A2A ProxyRoutes Agent2Agent (A2A) protocol traffic through Kong, with the same per-consumer auth and rate-limiting controls as other AI routes.

Load balancing algorithms (inside AI Proxy Advanced)

Configured via the Upstream entity, not separate plugins:

  • Round-robin (weighted) — proportional traffic split by weight.
  • Consistent-hashing — sticky sessions via a hashed header (default X-Kong-LLM-Request-ID).
  • Lowest-latency — routes to whichever target is currently fastest.
  • Lowest-usage — routes based on token/cost usage, including a cost option added to the usage strategy.
  • Priority — tiered failover (what we configured for Anthropic → Bedrock → OpenAI).
  • Semantic — routes prompts to domain-specialized models based on embedding similarity, with distance_metric and threshold controlling match sensitivity.
  • 3.13+ added health checks and a circuit breaker for the load balancer itself, plus failover/circuit-breaking for semantic routing specifically.

Governance & safety

PluginWhat it does
AI Prompt GuardBlocks or allows prompts by pattern/keyword rules.
AI Semantic Prompt GuardSame idea, but matches by embedding similarity rather than literal pattern — catches paraphrased attempts at a blocked topic. Enterprise.
AI Prompt DecoratorInjects or modifies system/user prompt content before it reaches the model (e.g. enforcing a system prompt).
AI Request/Response TransformerGeneral-purpose payload transformation for AI requests and responses.
AI Rate Limiting AdvancedRate limits by token count and cost, not just request count — this is the plugin underpinning the per-team quota story from the credential-governance duty. Enterprise.

Cost & performance

PluginWhat it does
AI Semantic CacheCaches responses by embedding similarity so repeated/similar prompts skip the model call entirely. Backed by a vector store (Redis and others). Enterprise.
AI RAG InjectorPulls relevant context from a vector store and injects it into the prompt for retrieval-augmented generation.

Observability

  • Prometheus plugin was extended with AI-specific metrics (token counts, cost, latency, MCP call volume) — this is what feeds the shared observability layer from the architecture summary.

Licensing note

Per Kong’s own docs and third-party comparisons: AI Proxy, AI Proxy Advanced, AI Prompt Guard, and AI Prompt Decorator are open source. AI Rate Limiting Advanced, AI Semantic Cache, AI Semantic Prompt Guard, and AI MCP Proxy sit behind Kong Enterprise/Konnect licensing. Confirm current tier gating against Kong’s plugin hub for your specific version, since this has shifted release to release.

Good — pulled the current plugin hub listing directly. Here’s the accurate, up-to-date table, tagged by license tier and mapped to the four pillars from the architecture doc.

AI Plugin Tier Table (Kong Plugin Hub, current)

Free / open source (no AI license required)

PluginWhat it does
AI ProxyBase multi-provider proxy and normalization
AI Prompt GuardPattern-based allow/deny list for prompts
AI Prompt DecoratorPrepends/appends messages to chat history
AI Prompt TemplateFill-in-the-blank prompt templates
AI Request TransformerLLM-based transform of the client request body
AI Response TransformerLLM-based transform of the upstream response

AI License Required (Enterprise/Konnect AI Gateway tier)

PluginWhat it does
AI Proxy AdvancedMulti-target proxy + load balancing/failover
AI Rate Limiting AdvancedToken/cost-based rate limiting
AI Semantic CacheEmbedding-based response caching
AI Semantic Prompt GuardEmbedding-based topic allow/deny
AI Semantic Response GuardBlocks/permits by similarity to known responses
AI PII SanitizerRedacts sensitive data in request/response bodies
AI Prompt CompressorShrinks prompts to cut cost/latency
AI RAG InjectorInjects vector-store content for RAG
AI MCP ProxyMCP server proxying, conversion, aggregation
AI MCP OAuth2OAuth2 auth for MCP servers
AI A2A ProxyGovernance for Agent-to-Agent protocol traffic
AI LLM as JudgeEvaluates/optimizes model output quality
AI AWS Guardrails / AI Azure Content Safety / AI GCP Model ArmorCloud-native guardrail integrations
AI Custom GuardrailBring-your-own third-party guardrails service
AI Lakera GuardLakera Guard safety-policy enforcement

Third-party (separate vendor licensing)
CrowdStrike Falcon AIDR (Request/Response/MCP), Harness AI Security, Noma Runtime Protection, Prisma AIRS, Skyflow De-identify, Straiker (+ Coding Agent variants), Impart Security, VeriKnox.

Mapped to the four architecture pillars

PillarPlugins that implement it
Credential GovernanceAI Proxy / AI Proxy Advanced (vault-referenced auth blocks); AI PII Sanitizer for data leaving the gateway
MCP Registry & GatewayAI MCP Proxy, AI MCP OAuth2
Multi-Provider FailoverAI Proxy Advanced (priority/weighted/semantic/lowest-latency/lowest-usage load balancing, plus 3.13+ health checks and circuit breaker)
ObservabilityPrometheus (extended with AI metrics), OpenTelemetry, AI LLM as Judge for quality tracking
(Guardrails — a fifth pillar worth adding)AI Prompt Guard, AI Semantic Prompt Guard, AI Semantic Response Guard, AI AWS/Azure/GCP Guardrails, AI Custom Guardrail, AI Lakera Guard

One correction from earlier: I’d said AI Prompt Guard and AI Prompt Decorator might be gated — they’re actually free/open source. AI Proxy Advanced, AI Rate Limiting Advanced, AI Semantic Cache, AI Semantic Prompt Guard, AI MCP Proxy and AI MCP OAuth2 are the ones that need the AI license.

I’d also flag that Guardrails has grown into its own real pillar — with cloud-native integrations (AWS/Azure/GCP) plus third-party options (Lakera, CrowdStrike, Straiker) — separate from what I’d folded into “credential governance” earlier.

Leave a Reply