Azure MCP Agents Functions
@jmnbc
Azure MCP Agents Functions について
Remote Azure DevOps MCP Server
基本情報
設定
ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
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.
Are there any known limits of Azure MCP Agents Functions?
The README does not mention any specific limits. Performance depends on Azure Functions quotas and Azure DevOps API rate limits.
「クラウドとインフラ」の他のコンテンツ
MCP Server that interacts with Azure AI Foundry (experimental)
azure-ai-foundryA MCP Server for Azure AI Foundry: it's now moved to cloud, check the new Foundry MCP Server
Firebase MCP
gannonh🔥 Model Context Protocol (MCP) server for Firebase.

Aws Kb Retrieval Server
modelcontextprotocolModel Context Protocol Servers
🐋 Docker MCP server
ckreilingMCP server for Docker
MCP Server Kubernetes
Flux159MCP Server for kubernetes management commands
コメント