What each is for, where Kong AI Gateway is strong, and how the two differ, capability by capability.
Kong Inc. · Based on the vendor's public documentation, last reviewed .
Kong AI Gateway
Kong AI Gateway routes model, MCP and A2A traffic through one gateway built on Kong Gateway. Its Enterprise MCP plugins expose REST APIs as MCP tools, validate OAuth tokens and apply per-tool access lists.
Managed through Kong Konnect, a SaaS control plane, with data planes that run self-hosted, in Kubernetes or as dedicated cloud gateways run by Kong. Self-managed deployments are also supported. The MCP plugins are part of the AI Gateway Enterprise offering.
Vekri
Runtime authorization for AI agents. Vekri Gateway checks every tool call against a verified identity, a task scope and Cedar policy; privileged writes wait for a person's approval of the exact operation; a broker executes with credentials the agent never sees.
In Vekri's cloud, or self-hosted in your Kubernetes cluster with no connection to Vekri.
Side by side
| Capability | What it means | Vekri | Kong AI Gateway |
|---|---|---|---|
| Decides each tool call inline | Every agent tool call is allowed or denied before it reaches the protected system. | Yes Vekri Gateway decides every MCP tool call sent through it before the broker executes it; a denied call never reaches the system. It is a boundary only when it is the only path to that system. | Documented The MCP proxy checks the caller against the tool's access list on each tool call and rejects a denied call with HTTP 403 before it reaches the upstream. [1] [3] |
| Verified workload identity | An agent running as a workload proves who it is with a credential the platform issued, not a shared key. | Yes Kubernetes projected service-account tokens, verified with TokenReview before Vekri issues a short-lived token for the run; every call is then authenticated. SPIFFE X.509-SVIDs from a configured trust bundle (no Workload API yet). | Partly Clients can authenticate with mTLS client certificates (Enterprise) or OAuth tokens, mapped to Kong consumers. Kubernetes service-account tokens and SPIFFE IDs are not described. [5] [2] |
| Employee agents use company SSO | Agents that employees run sign in as that employee, through the company identity provider. | Yes Vekri is the MCP authorization server for Claude Code and federates to your OpenID Connect provider. SAML sign-in is not available yet. | Documented The MCP OAuth2 plugin makes Kong the OAuth resource server under the MCP authorization specification, validating tokens issued by the organization's authorization server. [2] |
| Task-scoped permissions from the server | What an agent may do is set per task by the server, not by the agent or its prompt. | Yes A run scope for workloads, or a protected access assignment for employees. The effective permission is always an intersection, never a widening. | Not in public docs Access lists apply to consumers, consumer groups or token claims. A scope issued by the server for each task is not described in the public documentation. [3] |
| Policy as code, deny by default | Decisions come from versioned policy, and anything not allowed is refused. | Yes Cedar over typed operations. Unknown operations and evaluation errors are denied, and a revision can be simulated before it is published. | Partly Per-tool allow and deny lists, with deny taking precedence and denied tools removed from tool lists. A call is allowed when no list applies, and neither a policy language nor conditions on arguments is described. [3] [7] |
| Approval of the exact operation | A person approves one specific operation, and the approval cannot be reused for another. | Yes Privileged writes wait for another person to approve that operation, bound to its digest, short-lived and single use, with separation of duties. | Not in public docs Approval of an individual tool call by a person is not described in the public documentation. |
| Agent never holds backend credentials | Secrets for the protected system stay out of the agent's reach. | Yes A broker executes with narrowly scoped Kubernetes or GitHub App credentials. Incoming tokens are never forwarded. | Partly Client tokens validated by the MCP OAuth2 plugin are not forwarded by default and, from Kong Gateway 3.14, can be exchanged for an upstream token; AWS SigV4 signing is also available. The MCP proxy forwards other client request headers to upstreams by default. [2] [3] [7] |
| Audit evidence of decision and outcome | Each call leaves a durable record of what was decided and what happened. | Yes Intent is recorded durably before execution and the outcome after; an uncertain outcome is never retried blindly. | Documented Allowed and denied access attempts can be written to an audit log, with optional payload logging and export to OpenTelemetry. [1] [3] |
| AI agents on workstations | Finds AI coding agents and other AI applications on employee devices, and watches or controls what they do there. | Partly Vekri Endpoint discovers coding agents, desktop and IDE AI apps, local models and their MCP servers on macOS and Linux, and its local MCP gateway decides each MCP tool call sent through it (Claude Code verified connecting; tool calls verified with an MCP client library). On macOS, a network gateway mediates MCP requests to approved remote servers, and agent control stops AI agents the organization has not allowed. Hooks observe built-in tools without blocking them; Windows is not supported. | Not in public docs Discovering coding agents on employee devices is not described in the public documentation. |
| Prompt and output inspection | Detects prompt injection or sensitive data in what models read and write. | Partly Tool results on Vekri Gateway and the local MCP gateway are inspected for prompt injection before the agent reads them; sensitive-data categories are detected on the device, off by default. Browsers and file uploads are not inspected. | Partly Prompt guards, a PII sanitiser and cloud guardrail integrations check model traffic. Kong lists guardrails on MCP requests and responses as not supported. [4] [1] |
| Systems covered | Which systems, platforms or agents the product works with. | Kubernetes and GitHub, with GitLab, PostgreSQL, MySQL, MongoDB, Slack, Jira, Linear, Asana, ClickUp, monday.com, HubSpot, Pipedrive, Zendesk, Freshdesk and custom OpenAPI connectors in preview. | Model providers such as OpenAI, Anthropic, Azure AI, Amazon Bedrock and Gemini, plus MCP servers, REST APIs exposed as MCP tools, and A2A agents. An MCP Registry in the Konnect Catalog entered tech preview in February 2026. |
| Deployment | How the product is delivered. | In Vekri's cloud, or self-hosted in your Kubernetes cluster with no connection to Vekri. | Managed through Kong Konnect, a SaaS control plane, with data planes that run self-hosted, in Kubernetes or as dedicated cloud gateways run by Kong. Self-managed deployments are also supported. The MCP plugins are part of the AI Gateway Enterprise offering. |
Every agent tool call is allowed or denied before it reaches the protected system.
An agent running as a workload proves who it is with a credential the platform issued, not a shared key.
Agents that employees run sign in as that employee, through the company identity provider.
What an agent may do is set per task by the server, not by the agent or its prompt.
Decisions come from versioned policy, and anything not allowed is refused.
A person approves one specific operation, and the approval cannot be reused for another.
Secrets for the protected system stay out of the agent's reach.
Each call leaves a durable record of what was decided and what happened.
Finds AI coding agents and other AI applications on employee devices, and watches or controls what they do there.
Detects prompt injection or sensitive data in what models read and write.
Which systems, platforms or agents the product works with.
How the product is delivered.
More comparisons
Linux Foundation (created by Solo.io)
agentgateway is an open-source proxy for model, MCP and A2A traffic, hosted by the Linux Foundation. It authorizes MCP tools with CEL rules, accepts SPIFFE identities and exchanges tokens for backend credentials.
Cloudflare, Inc.
Cloudflare One gathers remote MCP servers behind portals protected by Cloudflare Access, with curated tools, managed OAuth and per-request logs. Gateway adds DLP and detects MCP traffic; AI Gateway handles model traffic.
Docker, Inc.
Docker's open-source MCP Gateway runs MCP servers in containers behind one endpoint. The paid Docker AI Governance tier adds Cedar policy for MCP tool calls, with rules on arguments and in-session confirmation.
IBM
ContextForge is IBM's open-source gateway and registry that federates MCP servers, A2A agents and REST or gRPC APIs behind one endpoint, with team-scoped roles, SSO, per-user OAuth to upstream servers and plugins.
Microsoft
Microsoft's open-source MCP Gateway deploys, scales and routes MCP servers and tools in Kubernetes behind one gateway, with a management API and portal, Entra ID sign-in and app roles on each server and tool.
Contact Sales
Talk to us about the AI your organization uses, the systems agents reach and how you deploy: in Vekri's cloud, or inside your own Kubernetes cluster.