What is the Model Context Protocol (MCP)?
MCP is a new protocol for tool‑calling in LLMs that powers structured AI‑agent communication.
@EXPESRaza
Basic information
A lightweight prototype demonstrating how to integrate an LLM (via OpenAI) with a Model Context Protocol (MCP) server to extract real-time weather data by scraping and processing open web content using HTML parsing and caching.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp_weather_scraper": {
"command": "python",
"args": [
"-m",
"venv",
".venv"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
An experimental MCP (Model Context Protocol) server that uses OpenAI and FastAPI to fetch and structure real-time weather information from open web sources. It is designed for developers exploring how LLMs can interact with tools to retrieve and reason over unstructured web data.
After cloning the repo, creating a virtual environment, installing dependencies, and setting the OPENAI_API_KEY environment variable, start the server with uvicorn server:app --reload. The server listens at http://localhost:8000. You can send a POST request to /weather with a JSON body containing a "location" field (e.g., {"location": "Seattle"}) using client.py or curl.
selectolax for performanceMCP is a new protocol for tool‑calling in LLMs that powers structured AI‑agent communication.
Python 3.9 or higher and dependencies listed in `requirements.txt`. You also need an OpenAI API key stored in a `.env` file.
The server performs a browser search on open web sources and uses `selectolax` (a high‑speed HTML parser) to extract raw weather content. The LLM then structures that content into a JSON response.
Yes, a Streamlit app frontend is included. It displays results along with response time, prompt tokens, completion tokens, and total tokens per request.
The server uses HTTP (FastAPI) and authenticates with an OpenAI API key via an environment variable. There is no additional authentication for the server endpoint itself.
MCP server paired with a browser extension that enables AI agents to control the user's browser.

Model Context Protocol Servers
MCP server for fetch web page content using Playwright headless browser.
Monitor browser logs directly from Cursor and other MCP compatible IDEs.
Let Claude Code, Claude Desktop, OpenAI Codex, Kimi and any MCP-capable AI agent create, launch, check and drive browser profiles in Nullprint, the AI antidetect browser. Install with one command.
Comments