Blog / Topic
Agent identity and access
Start here
All articles
How do you grant MCP server access by identity provider group?
Map IdP groups to policies, policies to per-user credentials, and credentials to MCP servers. Why shared application keys break group-based access.
How do you stop users gaining a service account's access through an AI agent?
On-behalf-of token exchange, permission intersection and authorisation at the tool stop users borrowing an agent service account's access. Decision table inside.
Can AI agents authenticate with SAML?
SAML is built for browser sign-in, so agents need OAuth tokens. How the SAML 2.0 bearer assertion grant (RFC 7522) and token exchange (RFC 8693) bridge the gap.
Can an LLM gateway reuse your existing Okta app for SSO?
One Okta OIDC app can hold several redirect URIs, but a separate app per tool limits blast radius. When to reuse, and the gateway SSO checklist.
What roles should an AI agent governance console have?
A role matrix for AI agent governance consoles: platform admin, security reviewer, agent owner, finance viewer and auditor, with separation-of-duties rules.
How can AI agents call Amazon Bedrock from outside AWS without long-term keys?
Credential options for agents and gateways calling Amazon Bedrock from outside AWS: IAM Roles Anywhere, web identity federation and short-term Bedrock API keys.
How long should an AI agent access token live?
Practical lifetimes for AI agent access and refresh tokens by risk tier, with platform defaults, RFC 9700 guidance and how revocation latency changes the answer.
What are OAuth Rich Authorization Requests and why do they matter for AI agents?
RFC 9396 authorization_details explained for AI agents: a payment example, scopes vs RAR compared, when to use it, and its practical limits.
How should privileged access management work for AI agents?
Vault agent credentials, check them out per task, inject them outside the model, record sessions. A PAM control map for AI agents with a rollout checklist.
How should users consent to an AI agent acting on their behalf?
An 8-point consent screen checklist for AI agents, incremental consent, when admin consent must replace user consent, and how to revoke grants.
What is CIBA and how can it get user approval for AI agent actions?
OpenID CIBA lets an AI agent ask a user to approve an action on their phone. The flow, poll vs ping vs push, binding messages, limits and a checklist.
What identity should an AI agent use when no user is present?
Scheduled and event-driven AI agents need their own workload identity, a named human owner and narrow scopes. A decision table for autonomous vs delegated modes.
Can SPIFFE and SPIRE give AI agents workload identity?
SPIFFE and SPIRE can give AI agent workloads a verifiable, short-lived identity. Here is what they cover, how attestation works, and what they leave open.
How do you track delegation chains when one AI agent calls another?
When agent A calls agent B for a user, keep the user, each actor and narrowing scopes in the token and the trace. A design for multi-hop delegation.
Should AI agents ever get break-glass access?
AI agents should not hold or trigger break-glass access themselves. Keep emergency access human-held, time-boxed and reviewed. A checklist for agent incidents.
RBAC or ABAC: which access model works for AI agents?
Roles are simple but explode for agents; attributes handle context but need clean data. A side-by-side table, agent-specific attributes and a hybrid pattern.
How does relationship-based authorisation (Zanzibar, OpenFGA) apply to AI agents?
ReBAC answers "can this agent, acting for this user, read this document?" How Zanzibar-style models work for agents and RAG, and check-at-retrieval vs check-at-index.
What is a joiner-mover-leaver process for AI agents?
Apply identity lifecycle to AI agents: the triggers for joiner, mover and leaver events, the access actions each requires, and a checklist your IAM team can run.
How do you give AI agents credentials without exposing them to the model?
Keep secrets out of prompts: inject credentials at the tool layer, use a token vault and short-lived tokens, and test that no secret ever appears in traces.
Should multiple AI agents share one service account?
Shared service accounts widen blast radius, erase attribution and block revoking one agent. How to migrate to one identity per AI agent, step by step.
Should AI agents use personal access tokens?
Personal access tokens tie an agent to one person's identity and permissions. Compare app installation tokens, bot tokens, workload identity and on-behalf-of access.
How do you give an AI agent safe read-only database access?
Dedicated role, narrow grants on views, row-level security, statement timeouts and a read replica, with example PostgreSQL grants for AI agents.
How should data classification labels control what AI agents can read?
Use sensitivity labels and catalogue tags as agent policy inputs: label-aware retrieval, per-classification model routing, blocking top-tier data externally.
How do you keep customer data separate in a multi-tenant AI agent?
Stop cross-tenant leaks in shared AI agents: propagate tenant context, filter retrieval and memory per tenant, scope credentials and caches, test for leaks.
How do you limit an AI agent's access to email and calendars?
Scope AI agent mailbox access: delegated vs application permissions, Exchange Online RBAC for Applications, and Google domain-wide delegation risks.
How do you stop an AI agent token from being used against the wrong API?
Bind agent tokens to one API with RFC 8707 resource indicators and audience checks, why MCP forbids token passthrough, and a test checklist per API.
Should AI agents use sender-constrained tokens like DPoP?
Bearer vs DPoP (RFC 9449) vs mTLS-bound tokens (RFC 8705) for AI agents: how each works, where each fits agent runtimes, and what binding cannot solve.
How do audit logs show which user an AI agent acted for?
Record both the user and the agent on every action: the RFC 8693 act claim, propagating user context through tool calls, and the log fields to capture.
Can AI agents use multi-factor authentication?
Why interactive MFA does not fit AI agents, the workload equivalents that achieve the same goal, and how to word the MFA policy exception for agents.
How do you revoke all of an AI agent's access at once?
Stop the agent in the request path, then revoke every credential type it holds in the right order, and test that each one now fails.
Can continuous access evaluation revoke an AI agent's access mid-task?
How OpenID Shared Signals and CAEP events like session-revoked reach AI agents, and the gap when long-running tasks hold cached access tokens.
Should AI agents have their own accounts in SaaS apps?
User-delegated access vs shared service account vs dedicated agent identity in SaaS apps: a comparison on audit, least privilege, revocation and licences.
How do you control what an AI agent can retrieve from a vector database?
Vector databases often connect straight to agents, bypassing MCP and gateway controls. How to enforce retrieval permissions server-side and log what was retrieved.
How should manual role overrides work when roles come from SCIM?
SCIM keeps roles in sync with your identity provider, but sometimes a role is wrong. Precedence rules, expiry, sync behaviour and audit for manual overrides.
Should SCIM or SSO group claims assign roles in an AI governance console?
Why a user provisioned by SCIM can land with the wrong role, how SCIM, group claims and JIT provisioning differ, and precedence rules for manual overrides.
Can AI agents use just-in-time access?
Just-in-time access for AI agents: short-lived tokens, session policies, token exchange and approval-gated elevation, with real AWS and Google Cloud lifetimes.
How do you control OAuth consent for AI apps and agents?
Control OAuth consent for AI apps: Entra and Google Workspace settings, a four-tier scope risk model, an admin consent workflow and grant reviews.
What Okta permissions does an AI governance tool need to map AI usage to employees?
Least-privilege Okta setup for mapping AI usage to employees: an API service app, read scopes, a read-only admin role and what each scope exposes.
How do you map identity provider groups to admin and viewer roles in an AI governance tool?
A least-privilege role set for AI governance consoles, a group-to-role mapping table, why admins show up as viewers, and tests to run after each sync.
How do you link AI usage records to employees when every tool uses a different identifier?
Build one identifier map for AI usage data: which IDs each tool emits, matching rules with confidence levels, and how to handle unmatched records.
Should AI agents use API keys or OAuth?
API keys vs OAuth for AI agents compared on revocation, scope, audit, user attribution and rotation, with when a key is still acceptable.
What does least privilege look like for an AI agent?
A twelve-point least-privilege checklist for AI agents covering identity, tokens, tools, data scopes, thresholds and expiry, with pass conditions.
How often should AI agent credentials be rotated?
Default token lifetimes for AWS, Google Cloud, Entra ID, Kubernetes and GitHub, eight triggers for immediate rotation, and how to retire static agent keys.
How do you run access reviews for AI agents?
A checklist for AI agent access reviews: fields to show reviewers, who signs off, revoke triggers, review frequency and the evidence to keep.
How does OAuth token exchange work for AI agents?
RFC 8693 token exchange lets an agent act for a user with a narrow, audience-bound token. Request parameters, the act claim, delegation vs impersonation.
Are AI agents non-human identities?
AI agents are non-human identities with extra risk. How they compare with service accounts and workload identities, and the six controls agents add.
How does workload identity federation work for AI agents?
Agents swap a signed OIDC token for short-lived cloud credentials instead of storing keys. How it works on AWS, Google Cloud and Microsoft Entra.
How do you assign an owner to every AI agent using your identity provider?
Map every AI agent to an owner in your IdP, apply joiner/mover/leaver rules to agents, and find orphaned agents when owners leave.
What happens to AI agents when their owner leaves the company?
Orphaned AI agents keep running on a leaver's keys and access. A step-by-step leaver workflow to find, reassign and re-credential every agent they owned.
Should AI governance tools allow local logins or SSO only?
Why AI governance tools should be SSO only, with SCIM provisioning, IdP group role mapping, a five-role model and two break-glass accounts.
Put the framework into practice