entra-agent-id

Erstellen und verwalten von OAuth2-fähigen Identitäten für KI-Agenten mit der Microsoft Graph Beta-API.

npx skills add https://github.com/microsoft/agent-skills --skill entra-agent-id

Microsoft Entra Agent ID

Create and manage OAuth2-capable identities for AI agents using Microsoft Graph beta API.

Preview API — All Agent Identity endpoints are under /beta only. Not available in /v1.0.

Before You Start

Search microsoft-docs MCP for the latest Agent ID documentation:

  • Query: "Microsoft Entra agent identity setup"
  • Verify: API parameters match current preview behavior

Conceptual Model

Agent Identity Blueprint (application)        ← one per agent type/project
  └── BlueprintPrincipal (service principal)   ← MUST be created explicitly
        ├── Agent Identity (SP): agent-1       ← one per agent instance
        ├── Agent Identity (SP): agent-2
        └── Agent Identity (SP): agent-3

Prerequisites

PowerShell (recommended for interactive setup)

# Requires PowerShell 7+
Install-Module Microsoft.Graph.Beta.Applications -Scope CurrentUser -Force

Python (for programmatic provisioning)

pip install azure-identity requests

Required Entra Roles

One of: Agent Identity Developer, Agent Identity Administrator, or Application Administrator.

Environment Variables

AZURE_TENANT_ID=<your-tenant-id>
AZURE_CLIENT_ID=<app-registration-client-id>
AZURE_CLIENT_SECRET=<app-registration-secret>

Authentication

⚠️ DefaultAzureCredential is NOT supported. Azure CLI tokens contain Directory.AccessAsUser.All, which Agent Identity APIs explicitly reject (403). You MUST use a dedicated app registration with client_credentials flow or connect via Connect-MgGraph with explicit delegated scopes.

PowerShell (delegated permissions)

Connect-MgGraph -Scopes @(
    "AgentIdentityBlueprint.Create",
    "AgentIdentityBlueprint.ReadWrite.All",
    "AgentIdentityBlueprintPrincipal.Create",
    "User.Read"
)
Set-MgRequestContext -ApiVersion beta

$currentUser = (Get-MgContext).Account
$userId = (Get-MgUser -UserId $currentUser).Id

Python (application permissions)

import os
import requests
from azure.identity import ClientSecretCredential

credential = ClientSecretCredential(
    tenant_id=os.environ["AZURE_TENANT_ID"],
    client_id=os.environ["AZURE_CLIENT_ID"],
    client_secret=os.environ["AZURE_CLIENT_SECRET"],
)
token = credential.get_token("https://graph.microsoft.com/.default")

GRAPH = "https://graph.microsoft.com/beta"
headers = {
    "Authorization": f"Bearer {token.token}",
    "Content-Type": "application/json",
    "OData-Version": "4.0",  # Required for all Agent Identity API calls
}

Core Workflow

Step 1: Create Agent Identity Blueprint

Sponsors are required and must be User objects — ServicePrincipals and Groups are rejected.

import subprocess

# Get sponsor user ID (client_credentials has no user context, so use az CLI)
result = subprocess.run(
    ["az", "ad", "signed-in-user", "show", "--query", "id", "-o", "tsv"],
    capture_output=True, text=True, check=True,
)
user_id = result.stdout.strip()

blueprint_body = {
    "@odata.type": "Microsoft.Graph.AgentIdentityBlueprint",
    "displayName": "My Agent Blueprint",
    "[email protected]": [
        f"https://graph.microsoft.com/beta/users/{user_id}"
    ],
}
resp = requests.post(f"{GRAPH}/applications", headers=headers, json=blueprint_body)
resp.raise_for_status()

blueprint = resp.json()
app_id = blueprint["appId"]
blueprint_obj_id = blueprint["id"]

Step 2: Create BlueprintPrincipal

This step is mandatory. Creating a Blueprint does NOT auto-create its service principal. Without this, Agent Identity creation fails with: 400: The Agent Blueprint Principal for the Agent Blueprint does not exist.

sp_body = {
    "@odata.type": "Microsoft.Graph.AgentIdentityBlueprintPrincipal",
    "appId": app_id,
}
resp = requests.post(f"{GRAPH}/servicePrincipals", headers=headers, json=sp_body)
resp.raise_for_status()

If implementing idempotent scripts, check for and create the BlueprintPrincipal even when the Blueprint already exists (a previous run may have created the Blueprint but crashed before creating the SP).

Step 3: Create Agent Identities

agent_body = {
    "@odata.type": "Microsoft.Graph.AgentIdentity",
    "displayName": "my-agent-instance-1",
    "agentIdentityBlueprintId": app_id,
    "[email protected]": [
        f"https://graph.microsoft.com/beta/users/{user_id}"
    ],
}
resp = requests.post(f"{GRAPH}/servicePrincipals", headers=headers, json=agent_body)
resp.raise_for_status()
agent = resp.json()

API Reference

OperationMethodEndpointOData Type
Create BlueprintPOST/applicationsMicrosoft.Graph.AgentIdentityBlueprint
Create BlueprintPrincipalPOST/servicePrincipalsMicrosoft.Graph.AgentIdentityBlueprintPrincipal
Create Agent IdentityPOST/servicePrincipalsMicrosoft.Graph.AgentIdentity
List Agent IdentitiesGET/servicePrincipals?$filter=...
Delete Agent IdentityDELETE/servicePrincipals/{id}
Delete BlueprintDELETE/applications/{id}

All endpoints use base URL: https://graph.microsoft.com/beta

Required Permissions

PermissionPurpose
Application.ReadWrite.AllBlueprint CRUD (application objects)
AgentIdentityBlueprint.CreateCreate new Blueprints
AgentIdentityBlueprint.ReadWrite.AllRead/update Blueprints
AgentIdentityBlueprintPrincipal.CreateCreate BlueprintPrincipals
AgentIdentity.Create.AllCreate Agent Identities
AgentIdentity.ReadWrite.AllRead/update Agent Identities

There are 18 Agent Identity-specific Graph application permissions. Discover all:

az ad sp show --id 00000003-0000-0000-c000-000000000000 \
  --query "appRoles[?contains(value, 'AgentIdentity')].{id:id, value:value}" -o json

Grant admin consent (required for application permissions):

az ad app permission admin-consent --id <client-id>

Admin consent may fail with 404 if the service principal hasn't replicated. Retry with 10–40s backoff.

Cleanup

# Delete Agent Identity
requests.delete(f"{GRAPH}/servicePrincipals/{agent['id']}", headers=headers)

# Delete BlueprintPrincipal (get SP ID first)
sps = requests.get(
    f"{GRAPH}/servicePrincipals?$filter=appId eq '{app_id}'",
    headers=headers,
).json()
for sp in sps.get("value", []):
    requests.delete(f"{GRAPH}/servicePrincipals/{sp['id']}", headers=headers)

# Delete Blueprint
requests.delete(f"{GRAPH}/applications/{blueprint_obj_id}", headers=headers)

Best Practices

  1. Always create BlueprintPrincipal after Blueprint — not auto-created; implement idempotent checks on both
  2. Use User objects as sponsors — ServicePrincipals and Groups are rejected
  3. Handle permission propagation delays — after admin consent, wait 30–120s; retry with backoff on 403
  4. Include OData-Version: 4.0 header on every Graph request
  5. Use Workload Identity Federation for production auth — for local dev, use a client secret on the Blueprint (see references/oauth2-token-flow.md)
  6. Set identifierUris on Blueprint before using OAuth2 scoping (api://{app-id})
  7. Never use Azure CLI tokens for API calls — they contain Directory.AccessAsUser.All which is hard-rejected
  8. Check for existing resources before creating — implement idempotent provisioning

References

FileContents
references/oauth2-token-flow.mdProduction (Managed Identity + WIF) and local dev (client secret) token flows
references/known-limitations.md29 known issues organized by category (from official preview known-issues page)
references/sdk-sidecar.mdMicrosoft Entra SDK for AgentID — endpoints, 3P agent patterns, Docker/K8s deployment, security

External Links

ResourceURL
Official Setup Guidehttps://learn.microsoft.com/en-us/entra/agent-id/identity-platform/agent-id-setup-instructions
AI-Guided Setuphttps://learn.microsoft.com/en-us/entra/agent-id/identity-platform/agent-id-ai-guided-setup
Microsoft Entra SDK for AgentID — Overviewhttps://learn.microsoft.com/en-us/entra/msidweb/agent-id-sdk/overview
Microsoft Entra SDK for AgentID — Endpointshttps://learn.microsoft.com/en-us/entra/msidweb/agent-id-sdk/endpoints

Mehr Skills von microsoft

oss-growth
microsoft
OSS-Wachstums-Hacker-Persona
official
microsoft-foundry
microsoft
Foundry-Agenten end-to-end bereitstellen, evaluieren und verwalten: Docker-Build, ACR-Push, gehostete/Prompt-Agenten erstellen, Container starten, Batch-Evaluierung, kontinuierliche Evaluierung, Prompt-Optimizer-Workflows, agent.yaml, Datensatzkuration aus Traces. VERWENDUNG FÜR: Agent in Foundry bereitstellen, gehosteten Agenten, Agenten erstellen, Agenten aufrufen, Agenten evaluieren, Batch-Evaluierung ausführen, kontinuierliche Evaluierung, kontinuierliches Monitoring, Status der kontinuierlichen Evaluierung, Prompt optimieren, Prompt verbessern, Prompt-Optimizer, Agentenanweisungen optimieren, Agenten verbessern...
officialdevelopmentdevops
azure-ai
microsoft
Verwendung für Azure AI: Suche, Sprache, OpenAI, Dokumentenintelligenz. Hilft bei Suche, Vektor-/Hybridsuche, Sprach-zu-Text, Text-zu-Sprache, Transkription, OCR. WANN: KI-Suche, Abfragesuche, Vektorsuche, Hybridsuche, semantische Suche, Sprach-zu-Text, Text-zu-Sprache, Transkribieren, OCR, Text in Sprache umwandeln.
officialdevelopmentapi
azure-deploy
microsoft
Führen Sie Azure-Bereitstellungen für BEREITS VORBEREITETE Anwendungen aus, die vorhandene .azure/deployment-plan.md- und Infrastrukturdateien haben. Verwenden Sie diese Fähigkeit NICHT, wenn der Benutzer darum bittet, eine neue Anwendung zu ERSTELLEN – verwenden Sie stattdessen azure-prepare. Diese Fähigkeit führt azd up, azd deploy, terraform apply und az deployment-Befehle mit integrierter Fehlerbehebung aus. Erfordert .azure/deployment-plan.md von azure-prepare und validierten Status von azure-validate. WANN: "run azd up", "run azd deploy", "execute deployment",...
officialdevopsaws
azure-storage
microsoft
Azure Storage-Dienste, darunter Blob Storage, Dateifreigaben, Queue Storage, Table Storage und Data Lake. Beantwortet Fragen zu Speicherzugriffsebenen (heiß, kühl, kalt, Archiv), wann welche Ebene verwendet werden sollte, und zum Vergleich der Ebenen. Bietet Objektspeicher, SMB-Dateifreigaben, asynchrone Nachrichtenübermittlung, NoSQL-Schlüssel-Wert und Big-Data-Analysen. Beinhaltet Lebenszyklusverwaltung. VERWENDUNG FÜR: Blob-Speicher, Dateifreigaben, Queue-Speicher, Table-Speicher, Data Lake, Dateien hochladen, Blobs herunterladen, Speicherkonten, Zugriffsebenen,...
officialdevelopmentdatabase
azure-diagnostics
microsoft
Debuggen von Azure-Produktionsproblemen mit AppLens, Azure Monitor, Ressourcenintegrität und sicherer Triage. WANN: Debuggen von Produktionsproblemen, Fehlerbehebung bei App Service, hohe CPU-Auslastung im App Service, Fehler bei der App Service-Bereitstellung, Fehlerbehebung bei Container-Apps, Fehlerbehebung bei Functions, Fehlerbehebung bei AKS, kubectl kann keine Verbindung herstellen, kube-system/CoreDNS-Fehler, ausstehende Pods, Crashloop, Knoten nicht bereit, Upgrade-Fehler, Analyse von Protokollen, KQL, Einblicke, Fehler beim Image-Pull, Probleme mit Kaltstarts, Fehler bei Integritätsprüfungen,...
officialdevopsdevelopment
azure-prepare
microsoft
Bereiten Sie Azure-Apps für die Bereitstellung vor (Infra Bicep/Terraform, azure.yaml, Dockerfiles). Verwenden Sie für Erstellen/Modernisieren oder Erstellen+Bereitstellen; nicht für Cross-Cloud-Migration (verwenden Sie azure-cloud-migrate). NICHT VERWENDEN FÜR: Copilot-SDK-Apps (verwenden Sie azure-hosted-copilot-sdk). WANN: "App erstellen", "Web-App erstellen", "API erstellen", "serverlose HTTP-API erstellen", "Frontend erstellen", "Backend erstellen", "Dienst erstellen", "Anwendung modernisieren", "Anwendung aktualisieren", "Authentifizierung hinzufügen", "Caching hinzufügen", "auf Azure hosten", "erstellen und...
officialdevelopmentdevops
azure-validate
microsoft
Vor der Bereitstellung durchgeführte Validierung der Azure-Bereitschaft. Führen Sie umfassende Prüfungen der Konfiguration, Infrastruktur (Bicep oder Terraform), RBAC-Rollenzuweisungen, verwalteten Identitätsberechtigungen und Voraussetzungen durch, bevor Sie bereitstellen. WANN: meine App validieren, Bereitstellungsbereitschaft prüfen, Preflight-Prüfungen durchführen, Konfiguration verifizieren, prüfen, ob bereit zur Bereitstellung, azure.yaml validieren, Bicep validieren, vor der Bereitstellung testen, Bereitstellungsfehler beheben, Azure Functions validieren, Funktionen-App validieren, serverlos validieren...
officialdevopstesting