Local Claude MCP Servers Collection
About
A collection of locally-hosted Model Calling Protocol (MCP) servers for extending Claude Desktop with external capabilities—such as weather retrieval and LinkedIn profile scraping—while keeping all data and processing under your control.
Explore
- Weather service for real-time location-based weather data
- LinkedIn profile scraper for extracting professional details
- Locally hosted to keep your data private and secure
- Simple JSON configuration in Claude Desktop
- Built with Python 3.9+ and uv for fast dependency management
- Planned expansions including document analysis and calendar integration
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
Local Claude MCP Servers CollectionCommand (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 3.9+ installed on your system
- Claude Desktop application
- Basic knowledge of command line operations
UV is a modern Python package installer and resolver that ensures fast, reproducible installations.
pip install uv
Find the exact path where UV is installed:
where uv # On Windows
which uv # On macOS/Linux
Take note of this path as you'll need it for the configuration.
To configure the MCP servers from this repository on your local machine:
{
"mcpServers": {
"weather": {
"command": "C:/Users/yourusername/AppData/Local/Programs/Python/Python311/Scripts/uv",
"args": [
"--directory",
"C:/path/to/your/MCP/weather",
"run",
"weather.py"
]
},
"linkedin_profile_scraper": {
"command": "C:/Users/yourusername/AppData/Local/Programs/Python/Python311/Scripts/uv",
"args": [
"--directory",
"C:/path/to/your/MCP/linkedin",
"run",
"linkedin.py"
]
}
}
}
> 📝 Note: Replace the paths in the configuration with your actual paths.
1. Visit Smithery.ai
2. Find and copy the command for your desired cloud-hosted MCP server
3. Run the command in your computer terminal
4. The MCP configuration file will be automatically updated
5. Restart Claude Desktop to use the new MCP servers
> 🚀 Pro Tip: Cloud-hosted MCP servers can complement your local ones, giving you the best of both worlds - local processing for sensitive tasks and cloud services for specialized capabilities without managing infrastructure.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"local claude mcp servers collection": {
"mcp-saptechengineer": {
"command": "uv",
"args": [
"venv"
]
}
}
}
}McpServers
{
"mcp-saptechengineer": {
"command": "uv",
"args": [
"venv"
]
}
}
A professional collection of locally-hosted Model Calling Protocol (MCP) servers for enhancing Claude Desktop with external capabilities while maintaining full control over your data and processing.
> ⭐ If you find this project useful, please consider giving it a star on GitHub to show your support! ⭐
Overview
This repository contains MCP servers that extend Claude Desktop with additional capabilities:
- Weather Service: Get real-time weather information for any location
- LinkedIn Profile Scraper: Extract and analyze professional profiles from LinkedIn
More MCP servers coming soon!
Project Structure
MCP/
├── linkedin/
│ ├── .venv/
│ ├── .env
│ ├── .gitignore
│ ├── linkedin.py
│ ├── pyproject.toml
│ └── uv.lock
├── weather/
│ ├── .venv/
│ ├── pyproject.toml
│ ├── requirements.txt
│ ├── uv.lock
│ └── weather.py
├── claude desktop config.png
└── README.md
Prerequisites
- Python 3.9+ installed on your system
- Claude Desktop application
- Basic knowledge of command line operations
Installation
1. Install UV
UV is a modern Python package installer and resolver that ensures fast, reproducible installations.
pip install uv
2. Verify UV Installation Path
Find the exact path where UV is installed:
where uv # On Windows
which uv # On macOS/Linux
Take note of this path as you'll need it for the configuration.
3. Clone the Repository
git clone https://github.com/yourusername/claude-mcp-servers.git
cd claude-mcp-servers
4. Set Up Each MCP Server
Each server is contained in its own directory with the necessary dependencies.
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
