Azure MCP Agents Functions

Name: Azure MCP Agents Functions
Author: jmnbc

@jmnbc

代码仓库

关于 Azure MCP Agents Functions

Remote Azure DevOps MCP Server

#azure-devops #mcp-tools #azure-functions

基本信息

分类

云与基础设施

许可证

MIT

运行时

传输方式

stdio

发布者

jmnbc

配置

暂无标准配置

该服务器的 README 中没有可解析的 MCP 配置块，请前往代码仓库查看安装说明。

代码仓库

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Azure MCP Agents Functions?

Azure MCP Agents Functions is a collection of Azure Functions that expose Azure DevOps capabilities as MCP (Model Context Protocol) Tools. It enables conversational AI interfaces to interact with Azure Boards and Azure Pipelines by listing projects, work items, and pipelines, creating work items, and triggering or checking pipeline runs.

How to use Azure MCP Agents Functions?

Clone the repository, update local.settings.json with your Azure DevOps organization URL, tenant ID, and client ID, ensure the Azure Storage Emulator is running (or configure a real storage account), and then run func start from the AzureMcpAgents.Functions directory. The tools become available for any MCP-compatible platform.

Key features of Azure MCP Agents Functions

Integrates with Azure Boards to list projects and work items
Creates work items (bugs, tasks, user stories) with details
Integrates with Azure Pipelines to list pipelines and trigger runs
Checks the status of specific pipeline runs
Exposes functions as MCP Tools using trigger and property attributes

Use cases of Azure MCP Agents Functions

Let a conversational AI create a new bug or task in Azure Boards
List all work items of a given type in a project via chat
Trigger a pipeline build from a natural language command
Check the status of a recent pipeline run without leaving the conversation

FAQ from Azure MCP Agents Functions

What are the dependencies to run Azure MCP Agents Functions?

The project requires the .NET SDK (compatible with .NET 8 or later), Azure Functions Core Tools, an Azure DevOps organization with a project, and an Azure Active Directory application registration with appropriate API permissions.

How does authentication to Azure DevOps work?

Authentication uses a VssConnection configured with the Vss__TenantId and Vss__ClientId values from local.settings.json. The connection likely employs a client secret or a similar mechanism, though it is not explicitly shown in the provided files.

Where does data processed by Azure MCP Agents Functions reside?

All data (projects, work items, pipelines) remains within Azure DevOps; the Functions act as a bridge and do not store any data themselves.

What transport does Azure MCP Agents Functions use?

The Azure Functions are triggered via the MCP framework, which typically uses HTTP. The exact transport details are not specified in the README beyond the Functions runtime.