Generated banner for Entra Agent Id
Generated logo for Entra Agent Id

Entra Agent Id

MicrosoftOfficialPublished by Microsoft

  • Skill
  • Tool integration
  • Security
  • MIT
  • Low risk

From the author

Microsoft Entra Agent ID (preview) for creating OAuth2-capable AI agent identities via Microsoft Graph beta API. Covers Agent Identity Blueprints, BlueprintPrincipals, Agent Identities, required permissions, sponsors, and Workload Identity Federation. Includes Microsoft Entra SDK for AgentID (containerized sidecar) for polyglot agent authentication (Docker/Kubernetes), 3P agent integration, autonomous and interactive agent patterns. Triggers: "agent identity", "agent id", "Agent Identity Blueprint", "BlueprintPrincipal", "entra agent", "agent identity provisioning", "Graph agent identity", "entra sidecar", "agent id sidecar", "auth sidecar", "3P agent", "third-party agent identity", "polyglot agent auth".
— the description by Microsoft

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

Microsoft Entra Agent ID provides a framework for creating and managing secure, OAuth2-capable identities for AI agents. This skill covers the lifecycle of agent identities, including the creation of Agent Identity Blueprints, BlueprintPrincipals, and individual Agent Identities. It details the necessary Microsoft Graph beta API interactions, required permissions, and authentication patterns such as Workload Identity Federation for production or client secrets for development.

What it does

  • Provision Agent Identity Blueprints to define agent types.
  • Create BlueprintPrincipals to enable agent identity functionality.
  • Generate individual Agent Identities for specific agent instances.
  • Configure Workload Identity Federation for secure production authentication.
  • Manage permissions and admin consent for Agent ID operations.
  • Perform cleanup of blueprints, principals, and agent identities.

When to use it

  • When building AI agents that require secure, OAuth2-based authentication within the Microsoft Entra ecosystem.
  • When deploying polyglot agents in containerized environments like Docker or Kubernetes.
  • When implementing autonomous or interactive agent patterns that need distinct service identities.
  • When managing third-party agent integrations that require standard identity provisioning.

Advantages

  • Enables standardized OAuth2 authentication for AI agents.
  • Supports secure production workflows via Workload Identity Federation.
  • Provides granular control over agent identity lifecycles.
  • Integrates directly with Microsoft Graph for programmatic management.

Usage examples

“How do I create an Agent Identity Blueprint using the Microsoft Graph API?”
The agent provides the JSON structure for a POST request to the /applications endpoint, including the required sponsor binding and OData type.
“What are the steps to set up Workload Identity Federation for my agent?”
The agent outlines the process of setting identifierUris, creating a federated identity credential on the blueprint, and configuring the Managed Identity for token exchange.

Install

  1. Download the skill as a ZIP:

    https://mp-staging.autogineer.com/agent-skills/microsoft/entra-agent-id/download
  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip entra-agent-id.zip -d .agents/skills

Documentation by Microsoft

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

# 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

Files

references/sdk-sidecar.md

Microsoft Entra SDK for AgentID: Polyglot Agent Authentication

Containerized companion service that handles token management for AI agents via HTTP — any language, any framework.

Preview — Image: mcr.microsoft.com/entra-sdk/auth-sidecar:<tag>. Check GitHub releases for tags.

Architecture

Client App → Your Agent (Python/Node/Go/Java) → Microsoft Entra SDK for AgentID (localhost:5000) → Microsoft Entra ID
                                                                    ↓
                                                              Downstream APIs

The Microsoft Entra SDK for AgentID runs as a companion container in the same pod or Docker network. Your agent calls it over HTTP — no SDK embedding required.

Agent Integration (3P and Custom Agents)

Third-party and custom agents authenticate using the Blueprint → BlueprintPrincipal → AgentIdentity hierarchy. The Microsoft Entra SDK for AgentID acquires tokens for these agent identities — whether you are building your own custom agent or integrating a third-party agent:

                        GET /AuthorizationHeaderUnauthenticated/graph
                              ?AgentIdentity={agent-app-id}
┌──────────────────┐   ─────────────────────────────────▶  ┌─────────────────────────────┐
│  Agent           │                                       │  Microsoft Entra SDK        │
│  (any language)  │   ◀─────────────────────────────────  │  for AgentID (:5000)        │
│                  │    { authorizationHeader:             │                             │
└────────┬─────────┘      "Bearer eyJ..." }                │  · AzureAd Config (Tenant,  │
         │                                                 │    ClientId, FIC)           │
         │                                                 │  · Agent Identity Params    │
         │                                                 │  · Downstream API Scopes    │
         │                                                 │  · Token Cache              │
         │                                                 └──────────────┬──────────────┘
         │                                                                │
         │ Authorization: Bearer <JWT>                                    │ OAuth 2.0
         ▼                                                                ▼
┌──────────────────────┐                                   ┌──────────────────────────┐
│  Downstream APIs     │                                   │  Microsoft Entra ID      │
│  · Microsoft Graph   │                                   │  · Blueprint             │
│  · Custom APIs       │                                   │  · AgentIdentity         │
│  · Azure Services    │                                   │                          │
└──────────────────────┘                                   └──────────────────────────┘

Microsoft Entra SDK for AgentID Configuration

Core Settings
env:
- name: AzureAd__Instance
  value: "https://login.microsoftonline.com/"
- name: AzureAd__TenantId
  value: "<your-tenant-id>"
- name: AzureAd__ClientId
  value: "<blueprint-app-id>"
Client Credentials

⚠️ Client secrets are for development only. Production deployments must use Federated Identity Credentials (FIC) via Workload Identity (SignedAssertionFilePath) or Managed Identity.

# Dev ONLY: Client Secret (do NOT use in production)
- name: AzureAd__ClientCredentials__0__SourceType
  value: "ClientSecret"
- name: AzureAd__ClientCredentials__0__ClientSecret
  value: "<secret>"

# Prod (AKS): Federated Identity Credentials via Workload Identity — RECOMMENDED
- name: AzureAd__ClientCredentials__0__SourceType
  value: "SignedAssertionFilePath"

# Prod (VM/App Service): Managed Identity
- name: AzureAd__ClientCredentials__0__SourceType
  value: "SignedAssertionFromManagedIdentity"
- name: AzureAd__ClientCredentials__0__ManagedIdentityClientId
  value: "<managed-identity-client-id>"
Downstream API
- name: DownstreamApis__Graph__BaseUrl
  value: "https://graph.microsoft.com/v1.0/"
- name: DownstreamApis__Graph__Scopes__0
  value: "https://graph.microsoft.com/.default"
- name: DownstreamApis__Graph__RequestAppToken
  value: "true"

Endpoint Reference

EndpointMethodAuth RequiredPurpose
/ValidateGETYesValidate inbound bearer token, return claims
/AuthorizationHeader/{name}GETYesValidate inbound token + acquire downstream token (OBO)
/AuthorizationHeaderUnauthenticated/{name}GETNoAcquire app/agent token without inbound user token
/DownstreamApi/{name}ANYYesValidate + call downstream API with auto token
/DownstreamApiUnauthenticated/{name}ANYNoCall downstream API with app/agent token
/healthzGETNoHealth probe
Agent Identity Query Parameters
ParameterPurposeExample
AgentIdentityAgent app (client) ID — autonomous mode?AgentIdentity=<agent-client-id>
AgentIdentity + AgentUsernameInteractive mode by UPN?AgentIdentity=<id>&[email protected]
AgentIdentity + AgentUserIdInteractive mode by Object ID?AgentIdentity=<id>&AgentUserId=<oid>

Rules:

  • AgentUsername/AgentUserId require AgentIdentity

  • AgentUsername and AgentUserId are mutually exclusive

  • AgentIdentity alone = autonomous agent

  • AgentIdentity + inbound bearer = interactive (OBO) agent

Code Patterns

Autonomous 3P Agent (Python)
import os
import requests

SIDECAR_URL = os.environ.get("SIDECAR_URL", "http://localhost:5000")
AGENT_APP_ID = os.environ["AGENT_CLIENT_ID"]

def get_agent_token(downstream_api: str = "Graph") -> str:
    """Acquire autonomous agent token via Microsoft Entra SDK for AgentID."""
    url = f"{SIDECAR_URL}/AuthorizationHeaderUnauthenticated/{downstream_api}"
    resp = requests.get(url, params={"AgentIdentity": AGENT_APP_ID}, timeout=30)
    resp.raise_for_status()
    return resp.json()["authorizationHeader"]

def call_downstream_api(endpoint: str) -> dict:
    """Call a downstream API using agent identity token."""
    token = get_agent_token()
    resp = requests.get(endpoint, headers={"Authorization": token}, timeout=10)
    resp.raise_for_status()
    return resp.json()
Interactive Agent with User Delegation (Python)
def get_delegated_token(user_token: str, downstream_api: str = "Graph") -> str:
    """Acquire delegated token via OBO flow."""
    url = f"{SIDECAR_URL}/AuthorizationHeader/{downstream_api}"
    resp = requests.get(
        url,
        headers={"Authorization": f"Bearer {user_token}"},
        timeout=30,
    )
    resp.raise_for_status()
    return resp.json()["authorizationHeader"]
Autonomous Agent (TypeScript)
const SIDECAR_URL = process.env.SIDECAR_URL ?? "http://localhost:5000";
const AGENT_APP_ID = process.env.AGENT_CLIENT_ID!;

async function getAgentToken(downstreamApi = "Graph"): Promise<string> {
  const url = `${SIDECAR_URL}/AuthorizationHeaderUnauthenticated/${downstreamApi}`;
  const res = await fetch(url + `?AgentIdentity=${AGENT_APP_ID}`);
  if (!res.ok) throw new Error(`Microsoft Entra SDK for AgentID error: ${res.status}`);
  const data = await res.json();
  return data.authorizationHeader;
}
Token Validation Middleware
def validate_incoming_token(bearer_token: str) -> dict:
    """Validate an incoming bearer token and extract claims."""
    resp = requests.get(
        f"{SIDECAR_URL}/Validate",
        headers={"Authorization": f"Bearer {bearer_token}"},
        timeout=10,
    )
    resp.raise_for_status()
    return resp.json()["claims"]
Direct Downstream Call via Microsoft Entra SDK for AgentID
def call_graph_me(user_token: str) -> dict:
    """Call Microsoft Graph /me via Microsoft Entra SDK for AgentID proxy."""
    resp = requests.get(
        f"{SIDECAR_URL}/DownstreamApi/Graph",
        params={"optionsOverride.RelativePath": "me"},
        headers={"Authorization": f"Bearer {user_token}"},
        timeout=10,
    )
    resp.raise_for_status()
    return resp.json()["content"]

Deployment

Docker Compose (Development)
version: '3.8'
services:
  sidecar:
    image: mcr.microsoft.com/entra-sdk/auth-sidecar:1.0.0-azurelinux3.0-distroless
    ports:
      - "5001:5000"
    environment:
      - AzureAd__Instance=https://login.microsoftonline.com/
      - AzureAd__TenantId=${TENANT_ID}
      - AzureAd__ClientId=${BLUEPRINT_APP_ID}
      - AzureAd__ClientCredentials__0__SourceType=ClientSecret
      - AzureAd__ClientCredentials__0__ClientSecret=${BLUEPRINT_CLIENT_SECRET}
      - DownstreamApis__Graph__BaseUrl=https://graph.microsoft.com/v1.0/
      - DownstreamApis__Graph__Scopes__0=https://graph.microsoft.com/.default
      - DownstreamApis__Graph__RequestAppToken=true
      - ASPNETCORE_URLS=http://+:5000

  agent:
    build: ./agent
    ports:
      - "3000:3000"
    environment:
      - SIDECAR_URL=http://sidecar:5000
      - AGENT_CLIENT_ID=${AGENT_CLIENT_ID}
    depends_on:
      - sidecar
Kubernetes (Production)
apiVersion: apps/v1
kind: Deployment
metadata:
  name: agent-deployment
spec:
  replicas: 3
  template:
    metadata:
      labels:
        app: agent
        azure.workload.identity/use: "true"
    spec:
      serviceAccountName: agent-sa
      containers:
      - name: agent
        image: myregistry/agent:latest
        env:
        - name: SIDECAR_URL
          value: "http://localhost:5000"
      - name: sidecar
        image: mcr.microsoft.com/entra-sdk/auth-sidecar:1.0.0
        ports:
        - containerPort: 5000
        env:
        - name: AzureAd__TenantId
          valueFrom:
            configMapKeyRef:
              name: agent-config
              key: tenant-id
        - name: AzureAd__ClientId
          valueFrom:
            configMapKeyRef:
              name: agent-config
              key: client-id
        - name: AzureAd__ClientCredentials__0__SourceType
          value: "SignedAssertionFilePath"
        - name: Kestrel__Endpoints__Http__Url
          value: "http://127.0.0.1:5000"
        resources:
          requests: { memory: "128Mi", cpu: "100m" }
          limits: { memory: "256Mi", cpu: "250m" }
        livenessProbe:
          httpGet: { path: /healthz, port: 5000 }
          initialDelaySeconds: 10
        readinessProbe:
          httpGet: { path: /healthz, port: 5000 }
          initialDelaySeconds: 5

Security

⚠️ The Microsoft Entra SDK for AgentID API must NOT be publicly accessible. Pod-local or same Docker network only.

  1. Bind to localhost — Kestrel__Endpoints__Http__Url=http://127.0.0.1:5000

  2. Never expose via LoadBalancer/Ingress

  3. Use Workload Identity in AKS — SignedAssertionFilePath over client secrets

  4. Use Key Vault for certificates — SourceType=KeyVault in production

  5. Separate ConfigMap from Secrets in Kubernetes

Troubleshooting

SymptomCauseFix
404 on /AuthorizationHeader/{name}{name} not in configAdd DownstreamApis__{name}__BaseUrl env var
400 AgentUsername requires AgentIdentityMissing AgentIdentity paramAlways pair user params with AgentIdentity
400 mutually exclusiveBoth AgentUsername and AgentUserIdUse one or the other
401 on /ValidateInvalid/expired inbound tokenCheck token audience matches AzureAd__ClientId
500 token acquisition failureWrong creds or missing admin consentkubectl logs <pod> -c sidecar
Connection refusedSDK not ready or wrong URLVerify SIDECAR_URL and /healthz

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs a command-line tool, Needs Python

Security

What our scanner noticed· Low risk

  • Instructions that use the network

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
Microsoft
Publisher
Microsoft (Official)
Source
microsoft/skills · .github/skills/entra-agent-id · commit 0696600
Licence
MIT License (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Microsoft.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download entra-agent-id.zip