广告合作
MCP.so
登录

MCP Server - FastAPI on Azure App Service

@learntocloud

代码仓库

基本信息

分类

开发工具

许可证

MIT license

传输方式

stdio

作者

learntocloud

关于 MCP Server - FastAPI on Azure App Service

暂无概览

MCP Server - FastAPI on Azure App Service 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "mcp-server-learntocloud": {
      "command": "python",
      "args": [
        "manage_api_keys.py",
        "list"
      ]
    }
  }
}

MCP Server - FastAPI on Azure App Service 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is MCP Server - FastAPI on Azure App Service?

A Python implementation of the MCP (Model Context Protocol) server using FastAPI, deployed to Azure App Service. It provides multiplication, temperature conversion, and weather tools, requiring API key authentication.

How to use MCP Server - FastAPI on Azure App Service?

Register for an API key via the public /register endpoint, then include the key in the Authorization: Bearer sk_... header when calling tools at /mcp-server/mcp/. For local development, set the MCP_AUTH_TOKEN environment variable to bypass Azure Storage authentication.

Key features of MCP Server - FastAPI on Azure App Service

  • Multiplication, Celsius/Fahrenheit conversion, and US weather alerts/forecast tools
  • Public API key registration with rate limiting (5 keys per email per 24 hours)
  • Admin script (manage_api_keys.py) to list, activate, deactivate, and create keys
  • Deployment to Azure App Service via Azure Developer CLI (azd up)
  • Local development with fallback MCP_AUTH_TOKEN authentication
  • Rate limiting: 1000 API requests per hour per key

Use cases of MCP Server - FastAPI on Azure App Service

  • Integrating MCP-compatible AI agents with arithmetic and weather functions
  • CTF (Capture The Flag) solutions requiring quick setup of an MCP server
  • Automating infrastructure scripts (Terraform) that call MCP tools
  • Server administrators monitoring key usage and managing registrations
  • Local development and testing with MCP Inspector

常见问题

1

How do I get an API key?

Send a `POST` request to the `/register` endpoint with your email, project name, and optional GitHub repo. The response includes an API key; save it securely.

2

What are the rate limits?

Registration: 5 API keys per email per 24 hours. API usage: 1000 requests per hour per key. Exceeding these returns a "Rate limit exceeded" error.

3

Why am I getting "Invalid authentication token"?

The API key may be incorrect, deactivated, or expired (if expiration is enabled). Verify the key and check the `Authorization` header format: `Bearer sk_...`.

4

How can I manage API keys as an administrator?

Use the `manage_api_keys.py` script to list, view, activate, deactivate, create, or delete keys. It also provides registration statistics.

5

What authentication modes are supported?

Production: Azure Managed Identity with API keys stored in Azure Table Storage. Development (fallback): `MCP_AUTH_TOKEN` environment variable, accepting any key starting with `sk_`.

评论

开发工具 分类下的更多 MCP 服务器

Cronwatch

cronwatchdev

CronWatch records every run of your scheduled jobs in your own database, and speaks up when one is missed, fails, gets stuck, runs slow or costs too much. CronWatch is free and open-source.

31

screenshotrun-mcp

screenshotrun

Give your AI agent the ability to see any webpage. Capture screenshots from Claude, Cursor, or any MCP client. Supports full-page, dark mode, mobile emulation, OG image generation, base64 output, custom viewport, ad bloc

OrangePro

Aamir Siddiqui

OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

12

Perfex CRM

themesic

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

1

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

1
广告合作