mcp-opentym
A lightweight MCP HTTP server giving AI assistants real tools to interact with your Windows machine, including running commands, file access, system info, web search, and browser automation.
README
š ļø mcp-opentym
A lightweight Model Context Protocol (MCP) HTTP server built with the official Python MCP SDK and Streamable HTTP transport. Designed to give AI assistants (Claude, Cursor, etc.) real tools to interact with your Windows machine.
⨠Features
| Tool | Description |
|---|---|
exec |
Run shell commands (cmd / PowerShell) |
read_file |
Read files with offset/limit pagination |
write_file |
Write or append to files |
list_files |
List directory contents |
open_app |
Open applications or URLs |
get_system_info |
CPU, RAM, disk, network info |
screenshot |
Capture the screen |
clipboard |
Read or write clipboard |
send_notification |
Windows toast notifications |
web_search |
Search the web via Brave API |
web_fetch |
Fetch and extract content from URLs |
http_request |
Generic HTTP client (GET/POST/etc.) |
get_datetime |
Current date & time |
calculate |
Safe math expression evaluator |
get_weather |
Weather by city name |
browser_action |
Full browser automation via Playwright |
memory_search |
Semantic search over memory files |
memory_get |
Read memory file snippets |
memory_write |
Append or write memory files |
š Quick Start
1. Clone & setup
git clone https://github.com/doanhtuan123/mcp-server-python.git
cd mcp-server-python
python -m venv .venv
.venv\Scripts\activate
pip install -r requirements.txt
playwright install chromium
2. Run the server
python server.py
Server starts at: http://localhost:3458/mcp
Health check: http://localhost:3458/health
3. Public tunnel (optional)
Expose locally via Cloudflare Quick Tunnel:
python tunnel.py
The public URL is saved to data/tunnel-url.txt.
āļø Configuration
| Item | Default |
|---|---|
| Port | 3458 |
| Transport | Streamable HTTP |
| Browser | Chrome (Playwright) |
| Shell | cmd / powershell |
To change the port, edit the port= value near the bottom of server.py.
š¦ Dependencies
mcp[cli]>=1.0.0
httpx>=0.27.0
beautifulsoup4>=4.12.0
playwright>=1.44.0
š Connect to Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"mcp-opentym": {
"url": "http://localhost:3458/mcp"
}
}
}
Or with the public tunnel URL:
{
"mcpServers": {
"mcp-opentym": {
"url": "https://<your-tunnel>.trycloudflare.com/mcp"
}
}
}
šļø Project Structure
mcp-server-python/
āāā server.py # Main MCP server
āāā tunnel.py # Cloudflare Quick Tunnel helper
āāā requirements.txt # Python dependencies
āāā data/ # Runtime data (logs, tunnel URL)
āāā workspace/ # Shared file workspace for tools
š License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.