skills.rest
microsoft
microsoftOFFICIAL
Explore all skills by this author →
Website𝕏@OpenAtMicrosoftGitHub

agent-framework-azure-ai-py

Build persistent Python agents for Azure AI Foundry with hosted tools and MCP integration.

2.9k|323|Updated Jan 16, 2026
Search Tags:#python#azure#mcp#conversations#agent-framework#azure-ai#hosted-tools
One-click install
npx skills add https://github.com/microsoft/skills --skill agent-framework-azure-ai-py-microsoft
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-framework-azure-ai-py
Source: https://github.com/microsoft/skills/tree/main/.github/plugins/azure-sdk-python/skills/agent-framework-azure-ai-py
Command: npx skills add https://github.com/microsoft/skills --skill agent-framework-azure-ai-py-microsoft

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a Python-based framework to build and manage persistent Azure AI Foundry agents using the Microsoft Agent Framework, enabling hosted tools, MCP integration, and threaded conversations for complex workflows.

Core Features & Use Cases

  • Provision persistent agents via AzureAIAgentsProvider and support hosted tools (code interpreter, file search, web search)
  • Integrate MCP servers and support streaming responses for dynamic workflows
  • Orchestrate multi-tool agents with structured outputs and cross-thread continuity

Quick Start

Install the agent-framework-azure-ai package, configure credentials, and instantiate a provider to create and run a persistent agent.

Frequently Asked Questions about agent-framework-azure-ai-py

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create persistent Azure AI agents with Python?▼

You can create persistent Azure AI agents with Python by installing the agent-framework-azure-ai package, configuring your Azure credentials, and instantiating the AzureAIAgentsProvider to provision and manage the agent lifecycle.

What are Azure AI hosted tools and how do they work with Python agents?▼

Azure AI hosted tools are built-in capabilities like code interpreter, file search, and web search that you can attach to a persistent Python agent. They allow the agent to execute code, query documents, and retrieve live web data.

Can I integrate MCP servers with Azure AI Foundry agents?▼

Yes, the framework supports MCP integration, allowing your Azure AI Foundry agents to connect to external MCP servers. This enables dynamic workflows and extends agent functionality with custom tools.

Do I need Azure credentials to use the Microsoft Agent Framework?▼

Yes, Azure credentials are strictly required to deploy and operate the framework. You must configure authentication before instantiating the provider to interact with the underlying Azure AI services.

How does multi-threaded conversation work in Azure AI agents?▼

Multi-threaded conversations allow a single persistent Azure AI agent to maintain cross-thread continuity across multiple distinct dialogue states. This enables structured outputs and complex multi-tool orchestration without losing context.

Related Skills

Explore More Software Engineering Skills→
microsoftmicrosoft
2.9k

azure-ai-projects-py

Manage Foundry agents, deployments, datasets, and evaluations with the azure-ai-projects Python SDK.

Official
Intermediate
eggboyeggboy

agent-framework-azure-ai-py

Orchestrate persistent Azure AI Foundry agents with hosted tools and MCP integration.

Community
Advanced
aiappsgbbaiappsgbb
5

foundry-toolbox

Connect agents to Microsoft Foundry Toolboxes via a Streamable HTTP MCP endpoint.

Official
Advanced
Kushal9889Kushal9889

agent-framework-azure-ai-py

Develops and deploys Azure AI agents using the Microsoft Agent Framework Python SDK.

Community
Advanced