What Python version is required?
Python 3.8 or higher is required.
@codingaslu
基本信息
A lightweight implementation of the Model Context Protocol (MCP) server using Server-Sent Events. Features a Wikipedia article parser that converts content to Markdown format. Demonstrates client-server MCP communication over HTTP.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"http-sse-mcp-starter": {
"command": "uv",
"args": [
"pip",
"install",
"-r",
"requirements.txt"
]
}
}
}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。
An HTTP SSE-based MCP (Model Context Protocol) server that provides a tool for fetching Wikipedia articles and converting them to Markdown format. It is built with FastMCP and intended for AI assistants and clients that use the Model Context Protocol.
Clone the repository, install dependencies with uv using uv pip install -r requirements.txt, then start the server with python server.py. The server listens on http://localhost:8000 with an SSE endpoint at /sse and a POST endpoint at /messages/. Clients can list server capabilities or fetch a Wikipedia article by passing the article URL as an argument.
Python 3.8 or higher is required.
All dependencies are listed in `requirements.txt` and must be installed using the `uv` package manager.
It uses Server-Sent Events (SSE) for real‑time communication from server to client and a separate POST endpoint (`/messages/`) for incoming messages.
It fetches an article from Wikipedia, parses its HTML content, and converts it to Markdown format.
Two endpoints: `/sse` for SSE connections and `/messages/` for handling POST requests.

The 9apes MCP server lets an AI assistant read the GitHub Actions data 9apes already collects for your organization: runs, jobs, steps, and their durations. Ask it why a build got slower, which jobs take the longest, or
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott
OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U
评论