Token导航 LogoToken导航

Agent Skill · 研究检索

entra-agent-id(内部 Agent ID)

entra-agent-id 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

entra-agent-id 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,674 个 Skill 里排第 1,633。

总安装 83,808周安装 3,563GitHub Stars 764下载 29,376核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:entra-agent-id(内部 Agent ID)
来源仓库:https://github.com/microsoft/azure-skills
仓库路径:skills/entra-agent-id
安装命令:
npx skills add https://github.com/microsoft/azure-skills --skill entra-agent-id
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

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

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

entra-agent-id 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。它为 AI 代理创建 OAuth 2.0 身份,提供独立的权限范围和审计追踪。

可通过 npx skills add 命令从指定仓库安装,需结合 Microsoft Graph API 使用。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/entra-agent-id

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/microsoft/azure-skills --skill entra-agent-id;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

entra-agent-id 怎么安装?

在终端执行 npx skills add https://github.com/microsoft/azure-skills --skill entra-agent-id。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

entra-agent-id 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

entra-agent-id 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

entra-agent-id 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

entra-agent-id 用的人多吗?

公开数据是累计安装 83,808 次,近一周安装 3,563 次,下载 29,376 次,GitHub 764 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

entra-agent-id 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
entra-agent-id

内部 Agent ID · 本页

83,808764接触敏感数据未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Microsoft Entra Agent ID

Create and manage OAuth 2.0-capable identities for AI agents using Microsoft Graph. Every agent instance gets a distinct identity, audit trail, and independently-scoped permission grants.

Quick Reference

PropertyValue
ServiceMicrosoft Entra Agent ID
APIMicrosoft Graph (https://graph.microsoft.com/v1.0)
Required roleAgent Identity Developer, Agent Identity Administrator, or Application Administrator
Object modelBlueprint (application) → BlueprintPrincipal (SP) → Agent Identity (SP)
Runtime exchangeTwo-step fmi_path exchange (autonomous and OBO)
.NET helperMicrosoft.Identity.Web.AgentIdentities
Polyglot helperMicrosoft Entra SDK for AgentID (sidecar container)

When to Use This Skill

  • Provisioning a new Agent Identity Blueprint and BlueprintPrincipal
  • Creating per-instance Agent Identities under a Blueprint
  • Configuring credentials (FIC, Managed Identity, or client secret) on the Blueprint
  • Implementing the two-step fmi_path runtime token exchange (autonomous or OBO)
  • Cross-tenant agent token flows
  • Deploying the Microsoft Entra SDK for AgentID sidecar for polyglot agents (Python, Node, Go, Java)
  • Granting per-Agent-Identity application (appRoleAssignments) or delegated (oauth2PermissionGrants) permissions
  • Diagnosing Agent ID errors such as AADSTS82001, AADSTS700211, or PropertyNotCompatibleWithAgentIdentity

MCP Tools

ToolUse
mcp_azure_mcp_documentationSearch Microsoft Learn for current Agent ID setup, Graph API shapes, and SDK configuration

There is no dedicated Agent Identity MCP server today. This skill guides direct Microsoft Graph API calls (PowerShell or Python requests). Use mcp_azure_mcp_documentation to verify request bodies and endpoints against current docs before running.

Before You Start

Use the mcp_azure_mcp_documentation tool to search Microsoft Learn for current Agent ID documentation:

  • "Microsoft Entra Agent ID setup instructions"
  • "Microsoft Entra SDK for AgentID"

Verify request bodies and endpoints against the installed SDK version — Graph API shapes evolve.

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
ConceptDescription
BlueprintApplication object that defines a type/class of agent. Holds credentials (secret, certificate, federated identity).
BlueprintPrincipalService principal for the Blueprint in the tenant. Not auto-created.
Agent IdentityService-principal-only identity for a single agent instance. Cannot hold its own credentials.
SponsorA User (or Group, for Agent Identity) who is responsible for the identity. Required on creation.

Prerequisites

Required Entra Roles

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

PowerShell (interactive setup)

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

Python (programmatic provisioning)

pip install azure-identity requests

Authentication

DefaultAzureCredential is not supported. Azure CLI tokens carry Directory.AccessAsUser.All, which Agent Identity APIs hard-reject (403). Use a dedicated app registration with client_credentials, or Connect-MgGraph with explicit delegated scopes.

PowerShell (delegated)

Connect-MgGraph -Scopes @(
    "AgentIdentityBlueprint.Create",
    "AgentIdentityBlueprint.ReadWrite.All",
    "AgentIdentityBlueprintPrincipal.Create",
    "AgentIdentity.Create.All",
    "User.Read"
)

Python (application)

import os, 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/v1.0"
headers = {
    "Authorization": f"Bearer {token.token}",
    "Content-Type": "application/json",
    "OData-Version": "4.0",
}

Core Workflow

Step 1: Create Agent Identity Blueprint

Use the typed endpoint. Sponsors must be Users at Blueprint creation. This snippet assumes the requests client and headers dict from the Python authentication block above.

import subprocess
import requests

user_id = subprocess.run(
    ["az", "ad", "signed-in-user", "show", "--query", "id", "-o", "tsv"],
    capture_output=True, text=True, check=True,
).stdout.strip()

blueprint_body = {
    "displayName": "My Agent Blueprint",
    "sponsors@odata.bind": [
        f"https://graph.microsoft.com/v1.0/users/{user_id}"
    ],
}
resp = requests.post(
    f"{GRAPH}/applications/microsoft.graph.agentIdentityBlueprint",
    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

Mandatory. Creating a Blueprint does NOT auto-create its service principal. Skipping this step produces: 400: The Agent Blueprint Principal for the Agent Blueprint does not exist.
sp_body = {"appId": app_id}
resp = requests.post(
    f"{GRAPH}/servicePrincipals/microsoft.graph.agentIdentityBlueprintPrincipal",
    headers=headers, json=sp_body,
)
resp.raise_for_status()

Make your provisioning scripts idempotent — always check for the BlueprintPrincipal even when the Blueprint already exists.

Step 3: Create Agent Identities

Sponsors for an Agent Identity may be Users or Groups.

agent_body = {
    "displayName": "my-agent-instance-1",
    "agentIdentityBlueprintId": app_id,
    "sponsors@odata.bind": [
        f"https://graph.microsoft.com/v1.0/users/{user_id}"
    ],
}
resp = requests.post(
    f"{GRAPH}/servicePrincipals/microsoft.graph.agentIdentity",
    headers=headers, json=agent_body,
)
resp.raise_for_status()
agent = resp.json()
agent_sp_id = agent["id"]

Runtime Authentication

Agents authenticate at runtime using credentials configured on the Blueprint (not on the Agent Identity — Agent Identities can't hold credentials).

OptionUse caseCredential on Blueprint
Managed Identity + WIFProduction (Azure-hosted)Federated Identity Credential
Client secretLocal dev / testingPassword credential
Microsoft Entra SDK for AgentIDPolyglot / 3P agentsSidecar container acquires tokens over HTTP

For the two-step fmi_path exchange (parent token → per-Agent-Identity Graph token) that gives each agent instance a distinct sub claim and audit trail, see references/runtime-token-exchange.md.

For OBO (agent acting on behalf of a user), see references/obo-blueprint-setup.md.

For the containerized polyglot auth sidecar (Python, Node, Go, Java — no SDK embedding), see references/sdk-sidecar.md.

For MI+WIF and client-secret setup details, see references/oauth2-token-flow.md.

.NET quick path

For.NET services, use Microsoft.Identity.Web.AgentIdentities — it handles Federated Identity Credential management and the two-step exchange for you. See the package README at github.com/AzureAD/microsoft-identity-web under src/Microsoft.Identity.Web.AgentIdentities/.

Granting Permissions (Per Agent Identity)

Agent Identities support both application permissions (autonomous) and delegated permissions (OBO). Grants are scoped per Agent Identity, not to the BlueprintPrincipal.

Application permissions (autonomous)

graph_sp = requests.get(
    f"{GRAPH}/servicePrincipals?$filter=appId eq '00000003-0000-0000-c000-000000000000'",
    headers=headers,
).json()["value"][0]

user_read_all = next(r for r in graph_sp["appRoles"] if r["value"] == "User.Read.All")

requests.post(
    f"{GRAPH}/servicePrincipals/{agent_sp_id}/appRoleAssignments",
    headers=headers,
    json={
        "principalId": agent_sp_id,
        "resourceId": graph_sp["id"],
        "appRoleId": user_read_all["id"],
    },
).raise_for_status()

Delegated permissions (OBO)

from datetime import datetime, timedelta, timezone

expiry = (datetime.now(timezone.utc) + timedelta(days=3650)).strftime("%Y-%m-%dT%H:%M:%SZ")

requests.post(
    f"{GRAPH}/oauth2PermissionGrants",
    headers=headers,
    json={
        "clientId": agent_sp_id,
        "consentType": "AllPrincipals",
        "resourceId": graph_sp["id"],
        "scope": "User.Read Tasks.ReadWrite Mail.Send",
        "expiryTime": expiry,
    },
).raise_for_status()

Browser-based admin consent URLs do not work for Agent Identities — use oauth2PermissionGrants for programmatic delegated consent.

Cross-Tenant Agent Identities

Blueprints can be multi-tenant (signInAudience: AzureADMultipleOrgs). When exchanging tokens cross-tenant:

Step 1 of the parent token exchange MUST target the Agent Identity's home tenant, not the Blueprint's. Wrong tenant → AADSTS700211: No matching federated identity record found.

See references/runtime-token-exchange.md for full cross-tenant examples.

API Reference

OperationMethodEndpoint
Create BlueprintPOST/applications/microsoft.graph.agentIdentityBlueprint
Create BlueprintPrincipalPOST/servicePrincipals/microsoft.graph.agentIdentityBlueprintPrincipal
Create Agent IdentityPOST/servicePrincipals/microsoft.graph.agentIdentity
Add FIC to BlueprintPOST/applications/{id}/microsoft.graph.agentIdentityBlueprint/federatedIdentityCredentials
List Agent IdentitiesGET/servicePrincipals/microsoft.graph.agentIdentity
Grant app permissionPOST/servicePrincipals/{id}/appRoleAssignments
Grant delegated permissionPOST/oauth2PermissionGrants
Delete Agent IdentityDELETE/servicePrincipals/{id}
Delete BlueprintDELETE/applications/{id}

Base URL: https://graph.microsoft.com/v1.0.

Required Graph Permissions

PermissionPurpose
AgentIdentityBlueprint.CreateCreate Blueprints
AgentIdentityBlueprint.ReadWrite.AllRead/update Blueprints
AgentIdentityBlueprintPrincipal.CreateCreate BlueprintPrincipals
AgentIdentity.Create.AllCreate Agent Identities
AgentIdentity.ReadWrite.AllRead/update Agent Identities
Application.ReadWrite.AllBlueprint CRUD on application objects
AppRoleAssignment.ReadWrite.AllGrant application permissions
DelegatedPermissionGrant.ReadWrite.AllGrant delegated permissions

Grant admin consent (required for application permissions):

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

After admin consent, tokens may not include new claims for 30–120 seconds — retry with exponential backoff.

Best Practices

  1. Always create BlueprintPrincipal after Blueprint — not auto-created.
  2. Use typed endpoints (/applications/microsoft.graph.agentIdentityBlueprint) instead of raw /applications with @odata.type.
  3. Credentials live on the Blueprint — Agent Identities can't hold secrets/certs (PropertyNotCompatibleWithAgentIdentity).
  4. Include OData-Version: 4.0 on every Graph request.
  5. Use Workload Identity Federation for production — client secrets only for local dev.
  6. Set identifierUris: ["api://{appId}"] on the Blueprint before OAuth2 scope resolution.
  7. Never use Azure CLI tokens for Agent Identity APIs — Directory.AccessAsUser.All causes hard 403.
  8. Use fmi_path with client_credentials — NOT RFC 8693 urn:ietf:params:oauth:grant-type:token-exchange (returns AADSTS82001).
  9. Always use /.default scope in both steps of the exchange — individual scopes fail.
  10. Step 1 targets the Agent Identity's home tenant in cross-tenant flows.
  11. Grant permissions per Agent Identity, not to the BlueprintPrincipal.
  12. Handle permission-propagation delays — retry 403s with 30–120s backoff after admin consent.
  13. Keep the Entra SDK for AgentID on localhost — never expose via LoadBalancer or Ingress.

Troubleshooting

ErrorCauseFix
AADSTS82001Used RFC 8693 token-exchange grantUse client_credentials with fmi_path
AADSTS700211Step 1 parent token targeted wrong tenantTarget Agent Identity's home tenant
AADSTS50013OBO user token targets Graph, not BlueprintUse api://{blueprint_app_id}/access_as_user
AADSTS65001Missing grant or used individual scopesUse /.default and verify oauth2PermissionGrants
403 Authorization_RequestDeniedNo grant on this Agent IdentityAdd via appRoleAssignments or oauth2PermissionGrants
PropertyNotCompatibleWithAgentIdentityTried to add credential to Agent Identity SPPut credentials on the Blueprint
Agent Blueprint Principal does not existBlueprintPrincipal not createdStep 2 of the Core Workflow
AADSTS650051 on admin consentSP already exists from partial consentGrant directly via appRoleAssignments

References

FileContents
references/runtime-token-exchange.mdTwo-step fmi_path exchange: autonomous + OBO, cross-tenant
references/oauth2-token-flow.mdMI + WIF (production) and client secret (local dev)
references/obo-blueprint-setup.mdConfiguring the Blueprint as an OAuth2 API for OBO
references/sdk-sidecar.mdMicrosoft Entra SDK for AgentID — architecture, configuration, endpoints
references/sdk-sidecar-deployment.mdSDK code patterns (Python/TypeScript), Docker/Kubernetes manifests, security, troubleshooting
references/known-limitations.mdDocumented gaps organized by category

External Links

平台分布

Codex

35.58%
按下载量换算10,452

Claude

32.58%
按下载量换算9,571

Cursor

18.05%
按下载量换算5,302

Gemini CLI

9.8%
按下载量换算2,879

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills