Agentic Identity IndexAgent controls / 2026 edition
Last verified 4 November 2026

Best for audit and lifecycle

Action attribution, policy decisions, revocation and ownership lifecycle.

Idira and Teleport 9.0 joint

Agent discovery 7.0 / Per-action policy 8.5 / Agent credentials 8.0

Watch out: Supported agent and MCP authentication types are bounded by the documented scope.

All 11 platforms are ranked on this criterion alone. A capability lead does not imply a lead on every buyer situation.

RankPlatformType / best forScoreEvidence
1=IdiraAgent identity brokerManaged mode records user and agent attribution on each tool call.9.0Review
Docs
2=TeleportInfrastructure and MCP accessPer-tool MCP audit events are documented across tiers.9.0Review
Docs
3=AstrixAgent discovery and provisioningPer-agent audit trails and ownership records are described.8.5Review
Docs
4=NewCoreAgent governance layerAction attribution and policy decisions provide an audit trail. Public retention and export limits need confirmation.8.5Review
Docs
5=AembitAgent and workload identity brokerMCP authorisation events can be traced in the documented logs.8.0Review
Docs
6=Clutch SecurityAgent identity guardrailsPolicy triggers and enforcement decisions include lineage context.8.0Review
Docs
7=DescopeAgent authentication and access hubAgent actions can be tied to the originating user in an audit trail.8.0Review
Docs
8=KeycardAgent access infrastructureTransaction telemetry and audit export are documented; plan limits apply.8.0Review
Docs
9=SailPoint EntroAgent discovery and credential governanceGovernance records and secret-exposure logs document ownership and activity.8.0Review
Docs
10Token SecurityAgent discovery and postureAgent action monitoring and multi-agent traceability are described.7.5Review
Docs
11SilverfortAgent identity securityMonitoring and visibility are described; detailed action export and retention need confirmation.7.0Review
Docs

What the score measures

Action attribution, policy decisions, revocation and ownership lifecycle. Scores reflect cited public documentation, not independent deployment tests.

Read the rubric and weights