entra-agent-id

Crie e gerencie identidades compatíveis com OAuth2 para agentes de IA usando a API beta do Microsoft Graph.

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

Mais skills de microsoft

oss-growth
microsoft
Persona de growth hacker OSS
official
microsoft-foundry
microsoft
Implantar, avaliar e gerenciar agentes Foundry de ponta a ponta: build Docker, push ACR, criação de agente hospedado/prompt, inicialização de contêiner, avaliação em lote, avaliação contínua, fluxos de trabalho do otimizador de prompt, agent.yaml, curadoria de conjunto de dados a partir de rastros. USE PARA: implantar agente no Foundry, agente hospedado, criar agente, invocar agente, avaliar agente, executar avaliação em lote, avaliação contínua, monitoramento contínuo, status da avaliação contínua, otimizar prompt, melhorar prompt, otimizador de prompt, otimizar instruções do agente, melhorar agente...
officialdevelopmentdevops
azure-ai
microsoft
Use para Azure AI: Search, Speech, OpenAI, Document Intelligence. Ajuda com pesquisa, busca vetorial/híbrida, fala para texto, texto para fala, transcrição, OCR. QUANDO: AI Search, pesquisa de consulta, busca vetorial, busca híbrida, busca semântica, fala para texto, texto para fala, transcrever, OCR, converter texto em fala.
officialdevelopmentapi
azure-deploy
microsoft
Execute implantações do Azure para aplicativos JÁ PREPARADOS que possuem arquivos .azure/deployment-plan.md e de infraestrutura existentes. NÃO use esta skill quando o usuário pedir para CRIAR um novo aplicativo — use azure-prepare. Esta skill executa comandos azd up, azd deploy, terraform apply e az deployment com recuperação de erros integrada. Requer .azure/deployment-plan.md do azure-prepare e status validado do azure-validate. QUANDO: "executar azd up", "executar azd deploy", "executar implantação",...
officialdevopsaws
azure-storage
microsoft
Serviços de Armazenamento do Azure, incluindo Blob Storage, File Shares, Queue Storage, Table Storage e Data Lake. Responde a perguntas sobre camadas de acesso ao armazenamento (hot, cool, cold, archive), quando usar cada camada e comparação entre elas. Oferece armazenamento de objetos, compartilhamentos de arquivos SMB, mensagens assíncronas, NoSQL chave-valor e análise de big data. Inclui gerenciamento de ciclo de vida. USE PARA: blob storage, file shares, queue storage, table storage, data lake, upload de arquivos, download de blobs, contas de armazenamento, camadas de acesso,...
officialdevelopmentdatabase
azure-diagnostics
microsoft
Depure problemas de produção no Azure usando AppLens, Azure Monitor, integridade de recursos e triagem segura. QUANDO: depurar problemas de produção, solucionar problemas do Serviço de Aplicativo, alto uso de CPU no Serviço de Aplicativo, falha de implantação do Serviço de Aplicativo, solucionar problemas de aplicativos em contêineres, solucionar problemas de funções, solucionar problemas do AKS, kubectl não consegue conectar, falhas do kube-system/CoreDNS, pod pendente, crashloop, nó não pronto, falhas de atualização, analisar logs, KQL, insights, falhas ao puxar imagem, problemas de inicialização a frio, falhas de sonda de integridade,...
officialdevopsdevelopment
azure-prepare
microsoft
Prepare aplicativos do Azure para implantação (infra Bicep/Terraform, azure.yaml, Dockerfiles). Use para criar/modernizar ou criar+implantar; não para migração entre nuvens (use azure-cloud-migrate). NÃO USE PARA: aplicativos copilot-sdk (use azure-hosted-copilot-sdk). QUANDO: "criar aplicativo", "construir aplicativo web", "criar API", "criar API HTTP serverless", "criar frontend", "criar backend", "construir um serviço", "modernizar aplicativo", "atualizar aplicativo", "adicionar autenticação", "adicionar cache", "hospedar no Azure", "criar e...
officialdevelopmentdevops
azure-validate
microsoft
Validação pré-implantação para prontidão do Azure. Execute verificações aprofundadas de configuração, infraestrutura (Bicep ou Terraform), atribuições de função RBAC, permissões de identidade gerenciada e pré-requisitos antes de implantar. QUANDO: validar meu aplicativo, verificar prontidão para implantação, executar verificações de pré-voo, verificar configuração, verificar se está pronto para implantar, validar azure.yaml, validar Bicep, testar antes de implantar, solucionar erros de implantação, validar Azure Functions, validar function app, validar serverless...
officialdevopstesting