Simple MCP Server
A simple MCP server that provides basic utility tools for text manipulation, file operations, and calculations, intended to be connected to Claude AI desktop app.
README
Simple Model Context Protocol (MCP) Server
A simple MCP server that provides basic utility tools for text manipulation, file operations, and calculations. This server can be connected to Claude AI desktop app to extend its capabilities.
Features
Available Tools:
- echo: Echo back any text you provide
- calculate: Perform basic mathematical calculations
- word_count: Count words, characters, and lines in text
- reverse_text: Reverse any text string
- uppercase: Convert text to uppercase
- list_files: List files and directories
- get_system_info: Get basic system information
Quick Setup
-
Run the setup script:
./setup.sh -
Or manual setup:
# Create virtual environment python3 -m venv venv source venv/bin/activate # Install dependencies pip install -r requirements.txt
Connecting to Claude AI Desktop App
Step 1: Locate Claude Configuration Directory
The configuration file location depends on your operating system:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
Step 2: Update Claude Configuration
- Find or create the configuration file at the location above
- Add the MCP server configuration:
{
"mcpServers": {
"simple-mcp-server": {
"command": "/Users/Projects/MCP/venv/bin/python",
"args": ["/Users/Projects/MCP/server.py"],
"env": {}
}
}
}
Important: Replace /Users/Projects/MCP/server.py with the actual absolute path to your server.py file.
Step 3: Restart Claude Desktop App
Close and restart the Claude desktop application completely.
Step 4: Test the Connection
- Open Claude desktop app
- In a new conversation, you should see MCP tools available
- Try asking Claude to use one of the tools, for example:
- "Can you calculate 15 * 23 for me?"
- "Please count the words in this text: 'Hello world this is a test'"
- "List the files in the current directory"
Testing the Server Manually
You can test the server directly:
# Activate virtual environment
source venv/bin/activate
# Run the server (it will wait for input)
python server.py
The server communicates via stdio (standard input/output) using JSON-RPC protocol.
Troubleshooting
Common Issues:
-
"Import mcp could not be resolved"
- Make sure you've installed the requirements:
pip install -r requirements.txt - Activate your virtual environment:
source venv/bin/activate
- Make sure you've installed the requirements:
-
Claude doesn't show MCP tools
- Check that the path in
claude_desktop_config.jsonis absolute and correct - Ensure Claude desktop app was completely restarted
- Check Claude's logs for any error messages
- Check that the path in
-
Server won't start
- Ensure Python 3.7+ is installed
- Check that all dependencies are installed
- Try running the setup script again
Configuration Example for Different Setups:
If using conda environment:
{
"mcpServers": {
"simple-mcp-server": {
"command": "conda",
"args": ["run", "-n", "your_env_name", "python", "/full/path/to/server.py"],
"env": {}
}
}
}
If using system Python:
{
"mcpServers": {
"simple-mcp-server": {
"command": "/usr/bin/python3",
"args": ["/full/path/to/server.py"],
"env": {}
}
}
}
Extending the Server
To add new tools:
- Add a new
Tooldefinition in thelist_tools()function - Add the corresponding handler in the
call_tool()function - Restart the server and Claude desktop app
Example Usage in Claude
Once connected, you can ask Claude to:
- "Calculate the square root of 144"
- "Count words in this paragraph: [your text]"
- "Convert this text to uppercase: hello world"
- "Show me what files are in my home directory"
- "What's my system information?"
File Structure
MCP/
├── server.py # Main MCP server code
├── requirements.txt # Python dependencies
├── setup.sh # Setup script
├── claude_desktop_config.json # Example Claude config
├── README.md # This file
└── venv/ # Virtual environment (created by setup)
Security Note
This server includes a basic calculate function that uses Python's eval(). In a production environment, you should replace this with a safer mathematical expression parser.
License
This project is provided as-is for educational and development purposes.
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.