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.
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_sessiontest_connectionget_auth_statusstart_interactive_sign_incomplete_interactive_sign_incomplete_interactive_loginconnect_intune_mcp_serverget_intune_overview
Intune and Entra Read Tools
manage_intune_devicesmanage_device_encryptionmanage_intune_appsmanage_app_config_mammanage_compliance_policiesmanage_configuration_profilesmanage_settings_catalogmanage_admx_policiesmanage_endpoint_securitymanage_security_baselinesmanage_windows_updatemanage_intune_scriptsmanage_intune_enrollmentmanage_autopilotmanage_filters_tagsmanage_intune_rbacmanage_cloud_pcmanage_entra_usersmanage_entra_groupsmanage_entra_devicesmanage_conditional_accessmanage_identity_protectionmanage_app_registrationsmanage_tenant_admin
Reporting Tool
manage_intune_reportslist_available_reportsexport_report(genericreportNamesupport)- Summary and scoped report actions (compliance, app install, analytics, encryption, enrollment failures, and related export jobs)
Catalog and Discovery
list_graph_catalog_operationsdescribe_graph_catalog_operationdiscover_graph_operations
Permissions
Use least privilege and only grant the scopes your scenario needs. Typical read permissions used by this server include:
Organization.Read.AllUser.Read.AllGroup.Read.AllAuditLog.Read.AllDevice.Read.AllDeviceManagementManagedDevices.Read.AllDeviceManagementConfiguration.Read.AllDeviceManagementApps.Read.AllDeviceManagementServiceConfig.Read.AllDeviceManagementRBAC.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
.envis 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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
E2B
Using MCP to run code via e2b.