The request asks what to use for an Agent Identity API. Microsoft Entra Agent ID is the most established option, provisioning agent identities via Microsoft Graph 111, with GitHub's Entra agent-user capability as a related option 212. Among the smaller products, AgentTrust issues and verifies agent identity codes 515, and Agent Trust Protocol offers an agent identity lookup 414.
- 1
Microsoft Entra Agent IDmicrosoft.comverified and signed
Provisions Microsoft Entra Agent Identity Blueprints and per-instance Agent Identities via Microsoft Graph, which is the agent identity API surface 11.
official:library · Microsoft.OpenApiskill · microsoft-foundryskill · appinsights-instrumentation+136 community tools built for it
for agents: entra-agent-id · create-custom-agent · hosted-agents-v2-py
- 2
GitHubgithub.comverified and signed
Creates Agent Users in Microsoft Entra ID from Agent Identities so AI agents can act with user identity capabilities 12.
official:CLI · github-mcp-serverskill · add-community-extensionskill · git-commitskill · acquire-codebase-knowledge+2,468 community tools built for it
for agents: entra-agent-user · create-agentsmd · agent-supply-chain
- 3
AgentTrustagenttrust.aiverified and signed
Issues and verifies cryptographic TrustCodes that prove an agent's identity, with no API key required for verification 15.
+6 community tools built for it
for agents: Verify TrustCode · Issue TrustCode · agenttrust_discover
- 4
- 5
Sources
- 1Microsoft – AI, Cloud, Productivity, Computing, Gaming & Appsmicrosoft.com · read 2026-10-29
- 2GitHub · Change is constant. GitHub keeps you ahead. · GitHub · GitHubgithub.com · read 2026-10-29
- 3AAuth Agent Identity, Resource Access, and User Delegationaauth.dev · read 2026-10-30
- 4Agent Trust Protocol™ | The Open Trust Layer for AI Agentsagenttrustprotocol.com · read 2026-10-30
- 5AgentTrust - A2A and Emails for AI Agentsagenttrust.ai · read 2026-10-29
- 11entra-agent-id: declares "entra-agent-id" (the record we read and signed)unfragile.ai · read 2026-10-24
- 12entra-agent-user: declares "entra-agent-user" (the record we read and signed)unfragile.ai · read 2026-10-24
- 14atp-core: declares "atp_identity_lookup" (the record we read)github.com · read 2026-10-24
- 15AgentTrust: declares "Verify TrustCode" (the record we read and signed)unfragile.ai · read 2026-10-24
For agents: the 10 actions behind this answer
entra-agent-id · entra-agent-id verified and signed
Provision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmi_path, OBO, cross-tenant) including the Microsoft Entra SDK for AgentID sidecar. USE FOR: Agent Identity Blueprint, BlueprintPri
entra-agent-user · entra-agent-user verified and signed
Create Agent Users in Microsoft Entra ID from Agent Identities, enabling AI agents to act as digital workers with user identity capabilities in Microsoft 365 and Azure environments.
· Aauth website read, tools not yet checked
Every agent gets its own cryptographic identity, verifiable by any party without pre-registration or shared secrets.
atp_identity_lookup · atp-core found in code, not yet checked
Look up ATP™ agent identity information
Verify TrustCode · AgentTrust verified and signed
Verify a TrustCode to confirm the identity of an agent. No API key required.
access-identity-providers-get-an-access-identity-provider · Cloudflare API verified and signed
Get an Access identity provider
use-link-identity · use-link-identity verified and signed
Use Link CLI's identity commands when a service requests a Link Agent Attestation Token (AAT) or signed user claims such as email. Covers acquiring and managing attestations, obtaining identity credentials, and presenting selected claims to a verifier through an HTTP client or browser automation.
· Cathedral-ai website read, tools not yet checked
Cathedral tracks AI agent identity across sessions drift detection, tamper-proof snapshots, and peer verification. Memory persistence included. Open source, self-hostable. Works with any model.
· AgentSIM website read, tools not yet checked
Operational identity for agents hitting auth walls. Verify apps you own, run a live SMS challenge, and return a code or safe stop into the agent workflow.
self_lookup_agent · self-agent-id found in code, not yet checked
Look up any agent's public identity by agent ID. Returns registration status, credentials, and verification details. No private key required.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.