What each is for, where Microsoft MCP Gateway is strong, and how the two differ, capability by capability.
Microsoft · Based on the vendor's public documentation, last reviewed .
Microsoft MCP Gateway
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.
Open source (MIT) and self-hosted on Kubernetes: locally with Docker Desktop's Kubernetes, or on Azure Kubernetes Service through a deployment template that provisions the supporting Azure resources.
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 | Microsoft MCP 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 Each MCP request is authenticated and authorized on its own before the gateway routes it to a server instance. Access is granted per MCP server or registered tool. [1] |
| 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 App roles can be assigned to service principals, which call the gateway with Entra ID tokens. Kubernetes service-account tokens or SPIFFE for calling agents are not described. [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 Cloud deployments require Entra ID bearer tokens, and clients such as VS Code handle the sign-in. Local development mode allows anonymous access. [1] |
| 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 follows app roles set on each server or tool. A scope issued by the server for each task is not described in the public documentation. [1] |
| 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 Read access to a server or tool goes to its creator, to holders of the app roles it lists, and to the mcp.admin role. The README's production guidance says to add finer-grained access control with RBAC or custom ACLs. [1] [2] |
| 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 Servers and tools the gateway deploys can use the cluster's Azure workload identity to reach Azure resources; by default only administrators can enable it. Whether a caller's token is forwarded to MCP servers is not described. [2] |
| 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. | Not in public docs The Azure deployment provisions Application Insights, and each server's logs can be read through the API. An audit record of each tool call's decision and outcome is not described in the public documentation. [1] |
| 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. | Not in public docs Inspection of prompts, tool arguments or results is not described in the public documentation. |
| 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. | MCP servers and tools packaged as container images, which the gateway deploys and scales in the cluster. It can also proxy existing local and remote MCP servers. |
| Deployment | How the product is delivered. | In Vekri's cloud, or self-hosted in your Kubernetes cluster with no connection to Vekri. | Open source (MIT) and self-hosted on Kubernetes: locally with Docker Desktop's Kubernetes, or on Azure Kubernetes Service through a deployment template that provisions the supporting Azure resources. |
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.
Kong Inc.
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.
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.