MCP Server Demo
MCP 服务器演示
模型控制协议 (MCP) 服务器实现的简单演示项目。未来将提供 MCP 客户端实现。
概述
该项目演示了一个使用 FastMCP 构建的简单 MCP 服务器,它为 AI 助手提供了多种工具和资源:
新闻文章获取:从 WorldNewsAPI 查询和检索新闻文章
简单计算:基本加法功能
天气信息:简单的天气数据检索
动态问候:个性化问候资源
Related MCP server: MCP Server Demo
设置
先决条件
Python 3.x
所需的 Python 包(用于测试):
mcp-serverworldnewsapi
安装
克隆此存储库
安装依赖项:
uv add mcp-serveruv add worldnewsapipip install mcp-server worldnewsapi
用法
运行服务器
使用 Python 运行服务器:从 MCP 相关配置并重新启动客户端,如 claude desktop 或 cursor ide mcp。
Available Tools
3 toolsaddC
Add two numbers
Inputs: a (required), b (required).
fetch_news_articlesB
Fetches news articles from the WorldNewsAPI based on specified parameters
and returns them as a list of dictionaries.
Args:
query_text (str): The text to search for in news articles
earliest_date (str): Earliest publication date in YYYY-MM-DD format
latest_date (str): Latest publication date in YYYY-MM-DD format
max_results (int): Maximum number of results to return
Returns:
list: A list of dictionaries containing article details
Inputs: query_text, earliest_date, latest_date, max_results.
get_weatherC
it gets and retuns the weather of the city
Inputs: city (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose with no overlap: 'add' performs arithmetic, 'fetch_news_articles' retrieves news data, and 'get_weather' provides weather information. The descriptions reinforce these unique domains, making misselection unlikely.
The naming is inconsistent with mixed conventions: 'add' uses a simple verb, 'fetch_news_articles' follows a verb_noun pattern with snake_case, and 'get_weather' uses a verb_noun pattern but with different verb style ('get' vs 'fetch'). This lack of pattern reduces predictability.
With only 3 tools, the server feels thin and under-scoped for a general-purpose 'MCP Server Demo', as it covers unrelated domains (math, news, weather) without depth in any area. This minimal set suggests a lack of coherent focus.
The tool set is severely incomplete for any discernible domain; it appears to be a random collection of unrelated utilities. There are obvious gaps, such as no update or delete operations for news or weather, and no coverage of basic workflows beyond simple fetches and addition.
Maintenance
Related MCP Connectors
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
MCP server exposing the Backtest360 engine API as tools for AI agents.
Related MCP Servers
- FlicenseCqualityDmaintenanceA demonstration server based on Model Context Protocol (MCP) that showcases how to build custom tools for AI assistants, providing mathematical calculation and multilingual greeting capabilities.3-
- AlicenseNot gradedqualityNot gradedmaintenanceA demonstration MCP server that provides calculator tools for arithmetic operations, personalized greeting resources, and code review prompt templates. Enables users to perform basic math calculations, generate dynamic greetings, and access reusable code review templates through the Model Context Protocol.MIT
- AlicenseNot gradedqualityDmaintenanceA minimal Model Context Protocol server demo that exposes tools through HTTP API, including greeting, weather lookup, and HTTP request capabilities. Demonstrates MCP server implementation with stdio communication and HTTP gateway functionality.ISC
- FlicenseNot gradedqualityCmaintenanceA basic MCP server implementation using the FastMCP framework that provides utility tools for greetings and mathematical calculations. It is designed to demonstrate tool integration for AI-assisted development workflows like Cline.-