# Decoy agent guides

- [AI authentication logic: how agents connect and sign in](https://www.decoys.me/guides/ai-agent-authentication.md): Authenticate the agent connection, verify the granted access, retrieve only the information needed for the task, then complete the service’s sign-in. Permission to use a credential is separate from permission to purchase, send or delete.
- [how to choose the best credential management for AI agents](https://www.decoys.me/guides/password-manager-for-ai-agents.md): For backend API calls, evaluate a secrets manager or credential broker. For user-owned accounts, evaluate an agent password manager with approved account access, website sign-in and verification email. In either case, verify secret handling, access expiry, revocation and the complete task.
- [how to secure AI agent credentials](https://www.decoys.me/guides/secure-ai-agent-credentials.md): Keep credentials in an encrypted store, grant only the access the task requires, decrypt in a trusted runtime and keep secrets out of chat and logs. Verify the result independently, track access and revoke or rotate credentials when needed.
- [how can ai agents handle 2FA?](https://www.decoys.me/guides/ai-agent-2fa.md): AI agents can handle 2FA by reading an approved service-specific inbox, requesting a current TOTP code, or asking the user’s phone to sign a passkey sign-in, which the user allows each time.
- [how should credential management work over MCP?](https://www.decoys.me/guides/mcp-credential-management.md): MCP credential management should pair a named agent, request specific resources, decrypt approved values locally and record each sensitive tool call without placing a whole password manager behind one tool.
- [how should passkeys work for ai agents?](https://www.decoys.me/guides/passkeys-for-ai-agents.md): An AI agent should use a passkey by sending the website’s challenge to the user’s phone, which signs it once the user allows that sign-in. The agent receives only the assertion; the private key never leaves the phone.
- [how can you give an ai agent email access safely?](https://www.decoys.me/guides/ai-agent-email-access.md): Give an AI agent access to a service-specific inbox or selected messages instead of connecting the user’s entire personal mailbox.
- [credential custody is not action authorization](https://www.decoys.me/guides/credential-custody-vs-action-authorization.md): Credential custody protects stored secrets. Access authorization controls retrieval. Action authorization controls what the authenticated agent may do. A safe system needs all three layers.
