What each is for, where Microsoft Entra Agent ID is strong, and how the two differ, capability by capability.
Microsoft · Based on the vendor's public documentation, last reviewed .
Microsoft Entra Agent ID
Microsoft Entra Agent ID gives AI agents their own identities in Entra, created from blueprints, and extends Conditional Access, ID Protection and governance to them. Access is decided when Entra issues a token.
Part of Microsoft Entra, delivered as a service. Agent ID is available to all Entra customers; extending Entra security features such as Conditional Access to agents requires Microsoft Agent 365 licensing.
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 Entra Agent ID |
|---|---|---|---|
| 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. | Not in public docs Conditional Access is evaluated when Entra issues or refreshes a token, and the resource authorizes each call from the token's claims. Global Secure Access can filter Copilot Studio agent traffic, but a decision on each tool call is not described. [3] [7] |
| 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). | Documented Managed identities are the preferred credential for agent identity blueprints, and workload identity federation lets agents on AWS or Google Cloud exchange their platform's token for an Entra token. [2] [4] |
| 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 Interactive agents act for a signed-in Entra user through the on-behalf-of flow, and Conditional Access applies that user's policies. [3] [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 Agents receive API permissions, group memberships or directory roles, which access packages can grant for a limited time. A scope issued for each task is not described. [5] |
| 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 Conditional Access policies allow, block or require more checks when a token is issued, targeting agent identities, blueprints or custom security attributes. Authorizing each request is left to the resource. [3] |
| 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. | Partly Access packages can require up to three approval stages before an agent receives time-bound permissions. Approval of a single operation is not described. [5] |
| 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 Managed identities, federation and the Auth SDK sidecar keep secrets out of agent code. The agent still receives an access token and calls the resource with it. [2] [4] |
| 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. | Partly Sign-in logs record agent sign-ins and audit logs record changes to agent identities. Recording each call made with a token is not described. [6] |
| 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 or monitoring coding agents on employee devices is not described in the Agent ID documentation. [1] |
| 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 Global Secure Access applies web content, threat intelligence and file filtering to Copilot Studio agent traffic. Inspecting prompts or model output is not described in the Agent ID documentation. [7] |
| 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. | Agents built with Microsoft tools such as Copilot Studio, and agents on AWS Bedrock, Google Cloud, n8n and other platforms through the Auth SDK sidecar or workload identity federation, reaching resources protected by Entra ID such as Microsoft Graph. |
| Deployment | How the product is delivered. | In Vekri's cloud, or self-hosted in your Kubernetes cluster with no connection to Vekri. | Part of Microsoft Entra, delivered as a service. Agent ID is available to all Entra customers; extending Entra security features such as Conditional Access to agents requires Microsoft Agent 365 licensing. |
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
Aembit
Aembit is an identity and access platform for workloads and AI agents. Edge components inject short-lived credentials into workload requests, and its MCP Identity Gateway applies access policy and tool rules to every MCP request.
Okta, Inc.
Okta for AI Agents registers agents as identities in Okta's directory and controls which resources they may reach. Agent Gateway, generally available since October 2026, proxies remote MCP servers and injects credentials into each tool call.
Delinea
StrongDM, now part of Delinea, proxies access to databases, servers, Kubernetes, clouds and MCP servers through nodes in your network. Cedar policy can allow or forbid individual MCP tools, and access can require approval.
Teleport
Teleport is an infrastructure access platform for people and machines. Its MCP access proxies MCP servers, allows or denies each tool by role, records every request, and issues short-lived credentials to users and bots.
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.