Remote Auth MCP Apim Py
R

Remote Auth MCP Apim Py

This project demonstrates how to deploy an MCP server protected by Entra ID on Azure, obtain Microsoft Graph tokens in a passwordless manner through the on-behalf-of flow, and implement it using API management and Azure functions.
2 points
6.2K

What is an Authenticated MCP Server?

This is a secure MCP server solution deployed on Azure, protected by Entra ID for authentication. It implements a keyless authorization mode where the client first obtains the MCP server token and then exchanges it for a Microsoft Graph access token through the on-behalf-of flow.

How to use this MCP service?

Users connect to the server endpoint through the Model Context Protocol Inspector tool. After completing Entra ID authentication, they can perform preset tool operations, such as querying Graph user information.

Applicable scenarios

Suitable for enterprise application scenarios that require secure access to Microsoft Graph, especially SaaS application integrations that require keyless management and fine-grained permission control.

Main features

Entra ID integrated authentication
Protect MCP endpoint access through enterprise-level authentication
On-Behalf-Of flow
Securely implement the conversion from the server token to the Graph access token
Keyless architecture
A secure design that does not handle sensitive credentials throughout the process
Graph tool integration
Preset standardized MCP tools for obtaining user details
Advantages
Enterprise-level security authentication guarantee
Automated infrastructure deployment (through Bicep)
A complete keyless implementation solution
Support for mainstream OAuth 2.0 authorization flows
Limitations
Currently, only the Model Context Protocol Inspector supports the complete authorization flow
Requires a specific version of the Inspector tool (0.9.0)
Deployment will incur Azure usage fees

How to use

Prepare the development environment
Install the Azure Developer CLI and the Node.js runtime environment
Deploy the infrastructure
Execute the azd up command to automatically deploy all Azure resources
Get the service endpoint
Copy the MCP endpoint URL provided by API Management from the deployment output
Connect to the MCP service
Use the MCP Inspector tool to connect to the endpoint and complete authentication

Usage examples

Get Graph user information
Query the basic profile of the currently logged-in user after authentication

Frequently Asked Questions

Why must a specific version of the MCP Inspector be used?
What Azure resources will be generated during deployment?
How to avoid unexpected costs?

Related resources

Azure Developer CLI documentation
Official installation and usage guide
MCP Inspector tool
A client tool for testing MCP services
On-Behalf-Of flow description
Microsoft's official authorization flow documentation

Installation

Copy the following command to your Client for configuration
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

R
Rsdoctor
Rsdoctor is a build analysis tool specifically designed for the Rspack ecosystem, fully compatible with webpack. It provides visual build analysis, multi - dimensional performance diagnosis, and intelligent optimization suggestions to help developers improve build efficiency and engineering quality.
TypeScript
7.9K
5 points
N
Next Devtools MCP
The Next.js development tools MCP server provides Next.js development tools and utilities for AI programming assistants such as Claude and Cursor, including runtime diagnostics, development automation, and document access functions.
TypeScript
9.5K
5 points
T
Testkube
Testkube is a test orchestration and execution framework for cloud-native applications, providing a unified platform to define, run, and analyze tests. It supports existing testing tools and Kubernetes infrastructure.
Go
6.2K
5 points
M
MCP Windbg
An MCP server that integrates AI models with WinDbg/CDB for analyzing Windows crash dump files and remote debugging, supporting natural language interaction to execute debugging commands.
Python
9.8K
5 points
R
Runno
Runno is a collection of JavaScript toolkits for securely running code in multiple programming languages in environments such as browsers and Node.js. It achieves sandboxed execution through WebAssembly and WASI, supports languages such as Python, Ruby, JavaScript, SQLite, C/C++, and provides integration methods such as web components and MCP servers.
TypeScript
7.6K
5 points
N
Netdata
Netdata is an open-source real-time infrastructure monitoring platform that provides second-level metric collection, visualization, machine learning-driven anomaly detection, and automated alerts. It can achieve full-stack monitoring without complex configuration.
Go
9.7K
5 points
M
MCP Server
The Mapbox MCP Server is a model context protocol server implemented in Node.js, providing AI applications with access to Mapbox geospatial APIs, including functions such as geocoding, point - of - interest search, route planning, isochrone analysis, and static map generation.
TypeScript
8.8K
4 points
U
Uniprof
Uniprof is a tool that simplifies CPU performance analysis. It supports multiple programming languages and runtimes, does not require code modification or additional dependencies, and can perform one-click performance profiling and hotspot analysis through Docker containers or the host mode.
TypeScript
7.3K
4.5 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
30.4K
5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
21.1K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
19.3K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
64.2K
4.3 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
58.4K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
27.2K
5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
41.8K
4.8 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
85.7K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase