Azure AI Agent Service MCP Server

Integrates with Azure AI Foundry to connect to existing Azure AI Agents, leveraging models and knowledge tools.

Remote serverstreamable-httpPython 227

What is the Azure AI Agent Service MCP server?

If you already use Azure AI Agent Service, the azure ai agent service mcp server is the piece that lets your assistant work with it directly. Integrates with Azure AI Foundry to connect to existing Azure AI Agents, leveraging models and knowledge tools.

What the server does

A Model Context Protocol server for Azure AI Foundry, providing a unified set of tools for models, knowledge, evaluation, and more.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • Models — The Models tool exposed by this server

Credentials and setup notes

Configuration is passed through the environment: GITHUB_TOKEN, AZURE_TENANT_ID, AZURE_CLIENT_ID, AZURE_CLIENT_SECRET, AZURE_AI_SEARCH_API_KEY, AZURE_OPENAI_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Installation

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

Where it fits

This sits in the cloud and infrastructure group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Azure AI Agent Service's toolset — Models — is a fair guide to whether it matches your workflow. It is maintained by azure-ai-foundry; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Azure AI Agent Service's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Worth knowing first

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
ModelsThe Models tool exposed by this server.

Configuration

VariableDescriptionRequired
GITHUB_TOKENCredential the server authenticates with.Yes
AZURE_TENANT_IDConfiguration value read at startup.Optional
AZURE_CLIENT_IDConfiguration value read at startup.Optional
AZURE_CLIENT_SECRETCredential the server authenticates with.Yes
AZURE_AI_SEARCH_API_KEYCredential the server authenticates with.Yes
AZURE_OPENAI_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Azure AI Agent Service to Models.

Frequently asked questions

Yes, the documentation provides configuration examples for using the Azure AI Agent Service with Claude Desktop, using both `uv` and `python` commands.