Cover image
Try Now
2025-04-14

A Model Context Protocol (MCP) server implementation for querying and managing Azure resources — built‑in support for Azure Managed Grafana, Azure Data Explorer (Kusto), Azure Resource Graph, Azure Resource Manager and more. Leverages User Identity or Managed Identity for secure, seamless integration via the C# MCP SDK.

3 years

Works with Finder

3

Github Watches

1

Github Forks

3

Github Stars

Blue Bridge

A Model Context Protocol (MCP) server for querying and managing Azure resources with zero‑secret authentication.
Out of the box it supports:

  • Azure Managed Grafana
  • Azure Data Explorer (Kusto)
  • Azure Resource Graph
  • Azure Resource Manager

Authentication is handled by the signed‑in Azure CLI account or a Managed Identity—no passwords or keys are stored.


✨ Demo

  1. Given 'manual-for-ai.md', get me the CPU quota for subscription '3a7edf7d-1488-4017-a908-e50d0a1642a6'

    Result

  2. Given 'manual-for-ai.md', show me 5 VMs that I can turn off machines to save money.

    Result

  3. Given 'manual-for-ai.md', help me find 2 VMs that I can turned off to save money. Please also turn them off. Please ask for permission for each VM before you do this.

    Result


🚀 Quick start

0 · Clone the repository

Clone the repository to get the necessary files, including recipes and usage examples found in manual-for-ai.md.

git clone https://github.com/Azure/blue-bridge.git
cd blue-bridge

1 · Run the container

Blue Bridge supports Azure Resource Graph and Azure Resource Manager out-of-the-box without any additional configuration.

To connect to Azure Managed Grafana or Azure Data Explorer (Kusto), set the corresponding environment variables when running the container.

Set the optional environment variables you need and start the image:

docker run --name bluebridge -p 6688:6688 \
  -e AzureManagedGrafanaEndpoint=https://<my‑grafana>.wcus.grafana.azure.com \
  -e KustoUri=https://<my‑kusto>.westus2.kusto.windows.net \
  bluebridge.azurecr.io/bluebridge:latest

If you only need Kusto:

docker run --name bluebridge -p 6688:6688 \
  -e KustoUri=https://<my‑kusto>.westus2.kusto.windows.net \
  bluebridge.azurecr.io/bluebridge:latest

Or with no external services:

docker run --name bluebridge -p 6688:6688 \
  bluebridge.azurecr.io/bluebridge:latest

2 · Authenticate once

On first start the container prints a device‑code prompt such as:

To sign in, use a web browser to open the page https://microsoft.com/devicelogin
and enter the code ABCD‑EFGH to authenticate.

Open the link, enter the code, and grant consent.
After that the server is ready at http://localhost:6688.

3 · Add to your MCP host

{
  "mcpServers": {
    "blue-bridge": {
      "url": "http://localhost:6688/sse",
      "transportType": "sse",
      "timeout": 60,
      "disabled": false,
      "autoApprove": []
    }
  }
}

4 · Run a quick test

Ask your MCP host:

Given 'manual-for-ai.md', show me 5 VMs that I can turn off machines to save money.

Result


🔧 Environment variables

Variable Purpose Required
AzureManagedGrafanaEndpoint Azure Managed Grafana endpoint URL No
KustoUri Azure Data Explorer (Kusto) cluster URI No
UseManagedIdentity Set to true to use managed identity. No
ManagedIdentityClientId Client ID of the managed identity to use. No

When UseManagedIdentity is set to true, Blue Bridge will attempt to authenticate using the managed identity available on the compute resource. This works automatically if there is only one managed identity (either system-assigned or user-assigned).

If the compute resource has multiple managed identities, you must specify which one to use by setting the ManagedIdentityClientId environment variable to the client ID of the desired managed identity. Note that setting ManagedIdentityClientId implies the use of managed identity, so setting UseManagedIdentity to true is not necessary in this case.


📚 Links

  • Docs & samples: https://aka.ms/blue-bridge

相关推荐

  • av
  • Effortlessly run LLM backends, APIs, frontends, and services with one command.

  • WangRongsheng
  • 🧑‍🚀 全世界最好的LLM资料总结(Agent框架、辅助编程、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型) | Summary of the world's best LLM resources.

  • 1Panel-dev
  • 🔥 1Panel provides an intuitive web interface and MCP Server to manage websites, files, containers, databases, and LLMs on a Linux server.

  • rulego
  • ⛓️RuleGo is a lightweight, high-performance, embedded, next-generation component orchestration rule engine framework for Go.

  • Azure
  • This repository is for development of the Azure MCP Server, bringing the power of Azure to your agents.

  • caio-moliveira
  • This project was created to demonstrate how we can connect with different Model Context Protocols (MCPs).

  • MarcusAdriano
  • Estudando MCP usando a API do Bacen PTAX

    Reviews

    2.8 (4)
    Avatar
    user_Atom0ija
    2025-04-24

    Blue-Bridge by Azure is an impressive product that bridges gaps seamlessly. The user-friendly interface and robust performance make it a highly effective application for various needs. Its reliability and efficiency have significantly enhanced my productivity. Highly recommend!

    Avatar
    user_q0xpdY4D
    2025-04-24

    Blue-Bridge by Azure is an exceptional tool that has truly enhanced my workflow. The integration is seamless, and the user interface is intuitive, making it easy to navigate and utilize its features effectively. I appreciate the robust functionality that caters to diverse needs, and the performance has been consistently reliable. Highly recommend!

    Avatar
    user_EMp8bYwR
    2025-04-24

    Blue-Bridge by Azure is a fantastic product! Its seamless integration and user-friendly interface make connecting cloud services a breeze. Highly recommend for anyone looking to streamline their workflows and enhance productivity. Easy to set up and reliable, it has become an indispensable part of my daily operations.

    Avatar
    user_VHrYwkjs
    2025-04-24

    Blue-Bridge by Azure is an exceptional MCP application! It provides seamless integration and a user-friendly interface, making it perfect for both beginners and professionals. The application is stable and efficient, significantly boosting productivity. Highly recommended for anyone looking to streamline their operations with Azure's robust technology!