MCP Server with Wikipedia Article Tool
About
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.
Explore
- MCP server implementation using FastMCP
- Server-Sent Events (SSE) for client-server communication
- Wikipedia article fetching tool
- Conversion of HTML content to Markdown
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
MCP Server with Wikipedia Article ToolCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
- Python 3.8+
- Dependencies listed in requirements.txt
- uv (Python package manager)
uv pip install -r requirements.txt
```
This is an HTTP SSE-based MCP (Model Context Protocol) server that features a tool for fetching and converting Wikipedia articles to Markdown.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp server with wikipedia article tool": {
"http-sse-mcp-starter": {
"command": "uv",
"args": [
"pip",
"install",
"-r",
"requirements.txt"
]
}
}
}
}
McpServers
{
"http-sse-mcp-starter": {
"command": "uv",
"args": [
"pip",
"install",
"-r",
"requirements.txt"
]
}
}
Features
- MCP server implementation using FastMCP - Server-Sent Events (SSE) for client-server communication - Wikipedia article fetching tool - Conversion of HTML content to MarkdownRequirements
- Python 3.8+ - Dependencies listed in requirements.txt - uv (Python package manager)Installation
```bashSign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



