Claude MCP Server Collection
@syedazharmbnr1
About Claude MCP Server Collection
MCP Server implementation for Claude
Basic information
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"ClaudeMCPServer": {
"command": "python3",
"args": [
"-m",
"venv",
".env"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is Claude MCP Server Collection?
Claude MCP Server Collection is a set of Model Context Protocol servers that extend Claude’s desktop application with screen capture, computer control, data analysis (DuckDB), HTTP requests (Curl), and FastAPI integration.
How to use Claude MCP Server Collection?
Clone the repository, create a Python virtual environment, install dependencies with pip install -r requirements.txt, then configure and start individual servers (e.g., python mcp_screen_server.py for screen capture, python fastapi/duckdb/main.py for DuckDB). Copy and update claude_desktop_config.json to integrate with the Claude Desktop app.
Key features of Claude MCP Server Collection
- Real‑time screen capture with dynamic image compression
- Mouse and keyboard automation with screen position tracking
- Fast SQL queries on CSV files larger than 1 GB via DuckDB
- HTTP request capabilities through a dedicated Curl server
- FastAPI integration for data processing and API endpoints
Use cases of Claude MCP Server Collection
- Analyze multi‑gigabyte CSV files directly in Claude Desktop
- Automate repetitive computer tasks (mouse clicks, keyboard shortcuts)
- Capture and process screenshots for visual context in conversations
- Make HTTP requests to external APIs from within Claude
- Build custom data processing pipelines using FastAPI endpoints
FAQ from Claude MCP Server Collection
What are the prerequisites?
Python 3.8 or higher, Node.js and npm (for the filesystem server), the Claude Desktop application, and Git.
How do I resolve port conflicts?
Default ports are: Screen Server 8767, FastAPI Server 8000, DuckDB Server 8010, and Integration Server 8768. Change them in the startup commands or environment variables.
What should I do if I get permission errors?
Make sure all Python scripts and shell scripts are executable by running chmod +x *.py and chmod +x Curl_Server/*.sh.
Where can I find error logs?
Each server component writes to its own log file; also check debug.log for detailed error messages.
What security precautions are mentioned?
Store GitHub tokens securely, never commit them to the repository, and configure filesystem paths carefully to limit access to necessary directories only.
More AI & Agents MCP servers
MCP-NixOS - Because Your AI Assistant Shouldn't Hallucinate About Packages
utensilsMCP-NixOS - Model Context Protocol Server for NixOS resources
MCP Server - Remote MacOs Use
baryhuangThe only general AI agent that does NOT requires extra API key, giving you full control on your local and remote MacOs from Claude Desktop App
Solon Ai
opensolonJava AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java25. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.
🔎 GPT Researcher
assafelovicAn autonomous agent that conducts deep research on any data using any LLM providers
Hass-MCP
voskaControl and query Home Assistant from Claude and other LLMs — a Model Context Protocol (MCP) server.
Comments