EndpointRead-MCP

EndpointRead-MCP

A read-only MCP server for Microsoft Intune and Entra ID that enables list, get, search, and reporting operations for tenant visibility, audits, troubleshooting, and health reporting without write actions. It includes authentication helpers, report exports, and metadata discovery tools.

Category
访问服务器

README

EndpointRead-MCP

Read-only Model Context Protocol (MCP) server for Microsoft Intune and Entra ID.

EndpointRead-MCP is a safe, non-destructive Graph MCP surface that supports list/get/search/reporting operations only. It is designed for tenant visibility, audits, troubleshooting, and health reporting without write actions.

Key Features

  • Read-only Intune and Entra operations.
  • Write actions are blocked by allowlist guards.
  • Built-in report export support for Intune reports.
  • Authentication helper tools for app/delegated/hybrid flows.
  • Metadata discovery tools for available operations.

Security Model

EndpointRead-MCP enforces read-only behavior in tool action dispatch. Destructive operations such as create/update/delete/assign/restart/wipe are not available. If a blocked action is requested, the tool returns an error with allowed actions.

Tool Catalog

Connection and Auth

  • authenticate_mcp_session
  • test_connection
  • get_auth_status
  • start_interactive_sign_in
  • complete_interactive_sign_in
  • complete_interactive_login
  • connect_intune_mcp_server
  • get_intune_overview

Intune and Entra Read Tools

  • manage_intune_devices
  • manage_device_encryption
  • manage_intune_apps
  • manage_app_config_mam
  • manage_compliance_policies
  • manage_configuration_profiles
  • manage_settings_catalog
  • manage_admx_policies
  • manage_endpoint_security
  • manage_security_baselines
  • manage_windows_update
  • manage_intune_scripts
  • manage_intune_enrollment
  • manage_autopilot
  • manage_filters_tags
  • manage_intune_rbac
  • manage_cloud_pc
  • manage_entra_users
  • manage_entra_groups
  • manage_entra_devices
  • manage_conditional_access
  • manage_identity_protection
  • manage_app_registrations
  • manage_tenant_admin

Reporting Tool

  • manage_intune_reports
    • list_available_reports
    • export_report (generic reportName support)
    • Summary and scoped report actions (compliance, app install, analytics, encryption, enrollment failures, and related export jobs)

Catalog and Discovery

  • list_graph_catalog_operations
  • describe_graph_catalog_operation
  • discover_graph_operations

Permissions

Use least privilege and only grant the scopes your scenario needs. Typical read permissions used by this server include:

  • Organization.Read.All
  • User.Read.All
  • Group.Read.All
  • AuditLog.Read.All
  • Device.Read.All
  • DeviceManagementManagedDevices.Read.All
  • DeviceManagementConfiguration.Read.All
  • DeviceManagementApps.Read.All
  • DeviceManagementServiceConfig.Read.All
  • DeviceManagementRBAC.Read.All

For report exports and advanced analytics, additional Intune read scopes may be required depending on endpoint/report type.

Configuration

Create .env in repo root (never commit it):

TENANT_ID=<your-tenant-id>
CLIENT_ID=<your-app-id>
CLIENT_SECRET=<your-client-secret>

AUTH_MODE=app
REQUIRE_USER_LOGIN=false
USER_AUTH_SCOPES=User.Read,DeviceManagementManagedDevices.Read.All
INTERACTIVE_LOGIN_MODE=browser
TOKEN_CACHE_PATH=.msal_token_cache.bin

Installation

cd E:\MCP\EndpointRead-MCP
py -3.13 -m venv .venv
.venv\Scripts\Activate.ps1
pip install -r requirements.txt
pip install -e .

Run

cd E:\MCP\EndpointRead-MCP
.venv\Scripts\python.exe -m intune_mcp_server.server

VS Code MCP Config Example

{
	"servers": {
		"EndpointRead-MCP": {
			"type": "stdio",
			"command": "E:\\MCP\\EndpointRead-MCP\\.venv\\Scripts\\python.exe",
			"args": ["-m", "intune_mcp_server.server"],
			"envFile": "E:\\MCP\\EndpointRead-MCP\\.env"
		}
	}
}

Secret Hygiene

  • .env is ignored by .gitignore.
  • Do not commit tenant secrets, access tokens, or cache files.
  • Rotate credentials if secrets are ever exposed.

Project Base

  • Derived from: IntuneRW-Core
  • Adapted to enforce read-only action allowlists
  • Includes one consolidated read reporting tool for Intune exports

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选