AI in the Cloud: Microsoft Foundry — The Agentic Developer Platform
Microsoft Ignite 2025 introduced Foundry, and it's positioned to be the central hub for building AI agents on Azure.
What Is Microsoft Foundry?
Think of it as the unified platform for everything agentic AI on Azure:
1. Unified MCP Tool Catalogue
The Model Context Protocol (MCP) finally gets a proper home. Foundry provides a catalogue of MCP-compatible tools that any AI agent can discover and use. No more reinventing integrations for every project.
2. Foundry Agent Service
A hosted multi-agent runtime with built-in memory. Deploy agents that can:
- •Maintain conversation state across sessions
- •Coordinate with other agents
- •Access enterprise data securely
3. Foundry Control Plane
Enterprise-grade observability and governance. This is where IT and security teams get visibility into what agents are doing, what data they're accessing, and how to enforce policies.
The Scale Is Impressive:
Azure now hosts over 11,000 models. Whether you want Claude, Gemini, Llama, or proprietary models — they're all accessible through the same platform.
Why This Matters for Cloud Engineers:
The agentic AI pattern is moving from experimentation to production. Foundry provides:
- •Standardization: MCP means your tools work across different AI models
- •Governance: Control Plane means you can actually deploy agents in regulated environments
- •Scalability: Azure's infrastructure handles the compute complexity
The Bigger Picture:
Microsoft, Anthropic, and NVIDIA just announced a massive partnership — $30B from Anthropic for Azure compute, $5B from Microsoft, $10B from NVIDIA invested in Anthropic.
Foundry is the platform that makes this partnership practical. Build once, deploy anywhere in the Azure ecosystem.
Getting Started:
- 1Explore Azure AI Foundry in the portal
- 2Check out the MCP tool catalogue
- 3Start with a single-agent prototype before scaling to multi-agent
The agentic era isn't coming. It's here.
Related Posts
Your AI Agent Has More Access Than Your Junior Devs. That Is a Security Bug.
AI agent security is no longer theoretical. Verified 2026 data shows widespread skill-level vulnerabilities, real malicious payloads, and measurable incident increases when agents are over-privileged. This guide translates the latest evidence into a least-agency security model for infrastructure teams.
MCP Is the USB-C of DevOps: The Governance Playbook Teams Need Before the First "Deploy Staging" Prompt
MCP has crossed from demo protocol to real platform plumbing for DevOps workflows, but the blocker is not model quality. It is governance: transport choices, identity, approval gates, server trust, auditability, and rollout discipline. This guide separates hype from what is actually production-relevant in Q1 2026.
DevSecOps for the Agent Era: The Security Gap Nobody's Talking About
Three CVE vulnerabilities hit Anthropic's MCP Git server. Docker acquired MCP Defender for runtime agent security. OWASP published a dedicated Top 10 for Agentic Applications. AI agents are shipping to production — but the security model hasn't caught up. Here's the agent security playbook.