Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@MCP Demo What's the current weather in Shanghai?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP (Model Context Protocol) Demo 是一个基于 FastMCP 框架的示例项目，展示了如何构建一个提供天气查询、随机倍数生成和股票行情获取功能的服务。该项目使用通义千问作为客户端，通过 FastMCP 服务器提供的工具接口实现各种功能。
Related MCP server: API Aggregator MCP Server
MCP Demo/
├── README.md # 项目说明文件
├── config.py # 配置文件
├── requirements.txt # 项目依赖
├── server.py # FastMCP 服务器实现
└── tongyi_client.py # 通义千问客户端服务器提供以下三个工具：
get_current_weather：获取指定城市的当前天气信息
get_num_rand：生成给定数字的随机倍数
get_stock_quote：获取指定股票的买卖盘数据
客户端使用通义千问 API，通过 MCP 协议调用服务器提供的工具，实现与用户的交互。
克隆项目到本地
安装项目依赖：
pip install -r requirements.txt配置 API 密钥：
编辑 config.py 文件，将 api_key 替换为实际的阿里云百炼 API 密钥。
python server.py服务器将在 http://0.0.0.0:8000 上运行。
python tongyi_client.py客户端启动后，您可以输入以下类型的问题：
"北京的天气怎么样？"
"生成 5 的随机倍数"
"获取股票 600000 的行情"
上传项目文件到服务器
配置服务器环境，确保安装了 Python 和必要的依赖
配置域名，外网映射，SSL等
启动命令：
uvicorn server:sse_app --host 0.0.0.0 --port 8000
服务器端：Python, FastMCP, Uvicorn
客户端：Python, Qwen Agent
依赖库：
akshare (1.18.14)：用于获取股票数据
fastmcp：MCP 框架
pydantic：数据验证
pandas：数据处理
uvicorn：ASGI 服务器
您可以通过运行客户端来测试各个工具：
确保服务器已经启动
运行客户端：python tongyi_client.py
输入测试问题，例如：
"上海的天气怎么样？"
"生成 7 的随机倍数"
"获取股票 600036 的行情"
确保已正确配置 API 密钥
服务器需要保持运行状态，客户端才能正常调用工具
股票行情查询需要使用正确的股票代码
天气查询功能依赖外部 API，可能会受到网络影响
user question: 上海的天气怎么样？
工具调用信息： {'name': 'get_current_weather', 'arguments': '{"city": "上海"}'}
工具调用结果： {"data": {"city": "上海", "date": "2026-02-26", "weather": "晴", "temp": "18℃", "humidity": "65%", "wind": "东北风 3级"}, "code": 0, "msg": "success"}
上海今天的天气是晴，温度18℃，湿度65%，东北风3级。
user question: 生成 7 的随机倍数
工具调用信息： {'name': 'get_num_rand', 'arguments': '{"num": 7}'}
工具调用结果： 49
7的随机倍数是49。
user question: 获取股票 600036 的行情
工具调用信息： {'name': 'get_stock_quote', 'arguments': '{"symbol": "600036"}'}
工具调用结果： [{"卖5价": 15.25, "卖5量": 1234, "卖4价": 15.24, "卖4量": 2345, "卖3价": 15.23, "卖3量": 3456, "卖2价": 15.22, "卖2量": 4567, "卖1价": 15.21, "卖1量": 5678, "买1价": 15.20, "买1量": 6789, "买2价": 15.19, "买2量": 7890, "买3价": 15.18, "买3量": 8901, "买4价": 15.17, "买4量": 9012, "买5价": 15.16, "买5量": 1013}]
股票600036的行情数据已获取，包括买卖盘价格和数量信息。Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
MCP server exposing the Backtest360 engine API as tools for AI agents.
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
The Dappier MCP server connects LLMs and AI agents to real-time, rights-cleared, proprietary data from trusted sources across various domains. It provides specialized knowledge through real-time web search, financial stock market and crypto data access, AI-powered content recommendations from premium publishers, and structured outputs with sub-300ms response times, enabling AI systems to respond to current events and trends.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/lakyia/MCPdemo'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
