MCPgee
MCPgee
MCPgeeMCPgee

Azure AI Vision Face API

v1.0.0•Data Science & ML•stable

The Azure AI Vision Face Detection and Recognition MCP Server, bringing the power of Face API to your agents.

azure-ai-vision-face-apimcpai-integration
Share:
9
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is Azure AI Vision Face API?

Azure AI Vision Face API is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to azure ai vision face detection and recognition mcp server, bringing the power of face api to your agents.

The Azure AI Vision Face Detection and Recognition MCP Server, bringing the power of Face API to your agents.

This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • The Azure AI Vision Face Detection and Recognition MCP Serve

Use Cases

Perform face detection and recognition using Azure AI Vision.
Integrate facial analysis capabilities into AI agents.
Azure-Samples

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMar 11, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx azure-ai-vision-face-api

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Azure AI Vision Face API

The Azure AI Vision Face API MCP Server brings Microsoft's Face API capabilities to AI agents through the Model Context Protocol, enabling face detection, facial attribute analysis, face recognition with person groups, and similarity-based face comparison. It optionally integrates with Azure OpenAI GPT-4.1 for open-set attribute detection beyond the built-in Face API attributes. The server is built in Python using the uv package manager and ships with an optional Node.js HTTP bridge for clients that cannot use stdio-based MCP transport.

Prerequisites

  • An Azure subscription with the Azure AI Face service resource created
  • Face API Endpoint URL and API Key from the Azure Portal (Keys and Endpoint blade)
  • Python 3.11 or later and uv package manager installed
  • Optional: Azure OpenAI resource with GPT-4.1 deployed for open-set attribute detection
  • Optional: Azure Blob Storage account and container for image storage
1

Clone the repository

Clone the Azure Samples repository for the Face API MCP server.

git clone https://github.com/Azure-Samples/azure-ai-vision-face-api-mcp-server.git
cd azure-ai-vision-face-api-mcp-server
2

Install uv

The project uses uv for Python dependency management. Install it if not already present on your system.

curl -LsSf https://astral.sh/uv/install.sh | sh
3

Set required environment variables

Export your Azure Face API credentials. These are mandatory for the server to start. Retrieve them from the Azure Portal under your Face resource's Keys and Endpoint section.

export AZURE_FACE_API_ENDPOINT="https://your-resource.cognitiveservices.azure.com/"
export AZURE_FACE_API_KEY="your_face_api_key"
4

Set optional Azure OpenAI and Storage variables

For open-set attribute detection with GPT-4.1 and for image storage workflows, set these additional environment variables.

export AZURE_OPENAI_ENDPOINT="https://your-openai-resource.openai.azure.com/"
export AZURE_OPENAI_API_KEY="your_openai_key"
export AZURE_STORAGE_ACCOUNT="yourstorageaccount"
export AZURE_STORAGE_CONTAINER="images"
export AZURE_STORAGE_SAS_TOKEN="sv=2024-..."
5

Configure Claude Desktop

Add the server to claude_desktop_config.json. Use uv run as the command so dependencies are resolved automatically without a manual install step.

{
  "mcpServers": {
    "azure-face-api": {
      "command": "uv",
      "args": ["run", "python", "-m", "mcp_server"],
      "cwd": "/path/to/azure-ai-vision-face-api-mcp-server",
      "env": {
        "AZURE_FACE_API_ENDPOINT": "https://your-resource.cognitiveservices.azure.com/",
        "AZURE_FACE_API_KEY": "your_face_api_key"
      }
    }
  }
}
6

Optional: run the HTTP bridge for non-stdio clients

If your MCP client does not support stdio transport, install and start the Node.js HTTP bridge to expose the server over HTTP.

cd bridge
npm install
npm run dev
# Bridge listens on http://localhost:3000
# Endpoints: GET /health, GET /mcp/tools, POST /mcp/call

Azure AI Vision Face API Examples

Client configuration

Claude Desktop configuration for the Azure Face API MCP server with mandatory credentials and optional storage variables.

{
  "mcpServers": {
    "azure-face-api": {
      "command": "uv",
      "args": ["run", "python", "-m", "mcp_server"],
      "cwd": "/Users/yourname/azure-ai-vision-face-api-mcp-server",
      "env": {
        "AZURE_FACE_API_ENDPOINT": "https://your-face-resource.cognitiveservices.azure.com/",
        "AZURE_FACE_API_KEY": "your_32_char_key_here",
        "AZURE_STORAGE_ACCOUNT": "yourstorageaccount",
        "AZURE_STORAGE_CONTAINER": "face-images",
        "AZURE_STORAGE_SAS_TOKEN": "sv=2024-08-04&..."
      }
    }
  }
}

Prompts to try

These prompts show how to invoke face detection, recognition, and attribute analysis through Claude.

- "Detect all faces in detection1.jpg and report which ones are wearing masks or glasses."
- "Create a new person group called 'team', enroll all images from the example/reco folder, and then identify the person in test.jpg."
- "Compare the face in photo_a.jpg to the face in photo_b.jpg and give me a similarity score."

Troubleshooting Azure AI Vision Face API

Server fails with 'AuthenticationFailure' on startup

Verify AZURE_FACE_API_KEY is the full key (32 hex characters) copied from the Azure Portal Keys blade, not the resource name or endpoint URL. Also confirm AZURE_FACE_API_ENDPOINT ends with a trailing slash.

Open-set attribute detection returns no results

This feature requires AZURE_OPENAI_ENDPOINT and AZURE_OPENAI_API_KEY to be set and a GPT-4.1 deployment to exist in your Azure OpenAI resource. Verify the deployment name matches what the server expects.

uv run fails with 'no pyproject.toml found'

Ensure you are running the command from the repository root directory, not a subdirectory. The pyproject.toml or uv.toml file must be present in the working directory for uv to resolve dependencies.

Frequently Asked Questions about Azure AI Vision Face API

What is Azure AI Vision Face API?

Azure AI Vision Face API is a Model Context Protocol (MCP) server that azure ai vision face detection and recognition mcp server, bringing the power of face api to your agents. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Azure AI Vision Face API?

Follow the installation instructions on the Azure AI Vision Face API GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Azure AI Vision Face API?

Azure AI Vision Face API works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Azure AI Vision Face API free to use?

Yes, Azure AI Vision Face API is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

Azure AI Vision Face API Alternatives — Similar Data Science & ML Servers

Looking for alternatives to Azure AI Vision Face API? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.

Ultrarag

★ 5.6k

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

RocketRide

★ 3.1k

📇 🏠 - MCP server that exposes RocketRide AI pipelines as t

Aix Db

★ 2.1k

Aix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。

NeMo Data Designer

★ 1.9k

🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.

PaperBanana

★ 1.7k

Open source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.

MiniMax

★ 1.5k

Bridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.

Browse More Data Science & ML MCP Servers

Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Data Science & MLBrowse All Servers

Quick Config Preview

{ "mcpServers": { "azure-ai-vision-face-api": { "command": "npx", "args": ["-y", "azure-ai-vision-face-api"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Azure AI Vision Face API?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides