MCP Multi-Tool Server
Provides calculator tools for mathematical operations, access to TypeScript SDK documentation, and meeting summary prompt templates through both stdio and SSE transports.
README
MCP Multi-Tool Server
A comprehensive Model Context Protocol (MCP) server that provides calculator tools, documentation resources, and prompt templates. This server supports both stdio and SSE (Server-Sent Events) transports, making it compatible with various MCP clients including Claude Desktop.
Features
🧮 Calculator Tools (8 Tools)
- add - Add two numbers
- subtract - Subtract two numbers
- multiply - Multiply two numbers
- divide - Divide two numbers
- power - Raise a number to a power
- square_root - Calculate square root
- factorial - Calculate factorial
- calculate_percentage - Calculate percentage
📚 Resources
- TypeScript SDK Documentation - Access the full TypeScript SDK MCP documentation via resource URI
typescript-sdk-mcp://documentation
📝 Prompts
- Meeting Summary - Generate executive meeting summaries from transcripts using a customizable template
🔌 Transport Support
- stdio (default) - Standard input/output for local integrations
- SSE - Server-Sent Events for remote HTTP connections
Table of Contents
- Prerequisites
- Installation
- Quick Start
- Usage
- Transport Modes
- Connecting to Claude Desktop
- API Reference
- Project Structure
- Troubleshooting
- Contributing
- License
Prerequisites
- Python 3.10+ (Python 3.12 recommended)
- uv - Fast Python package installer
- Administrative privileges (for software installation)
Installation
Step 1: Install Python
Windows
- Download Python from python.org/downloads
- Run the installer and check "Add Python to PATH"
- Verify installation:
python --version pip --version
macOS
# Using Homebrew (recommended)
brew install python@3.12
# Or download from python.org
Linux (Ubuntu/Debian)
sudo apt update
sudo apt install python3 python3-pip python3-venv -y
Step 2: Install uv
Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
Close and reopen PowerShell, then verify:
uv --version
macOS/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
Add to PATH if needed:
export PATH="$HOME/.cargo/bin:$PATH"
Verify:
uv --version
Step 3: Clone and Setup
# Clone the repository
git clone <your-repo-url>
cd mcp-multi-tool-server
# Initialize project
uv init --no-readme
# Create virtual environment
uv venv
# Activate virtual environment
# Windows PowerShell:
.\.venv\Scripts\Activate.ps1
# Windows CMD:
.venv\Scripts\activate.bat
# macOS/Linux:
source .venv/bin/activate
# Install dependencies
uv add "mcp[cli]"
Quick Start
Running with stdio (Default)
# Activate virtual environment first
source .venv/bin/activate # or .\.venv\Scripts\Activate.ps1 on Windows
# Run the server
python server.py
The server will start in stdio mode, ready to accept connections from MCP clients.
Running with SSE
# Set transport to SSE
TRANSPORT=sse python server.py
# Or with custom host/port
TRANSPORT=sse HOST=0.0.0.0 PORT=8000 python server.py
The server will start an HTTP server on the specified host and port, accessible via SSE.
Usage
Environment Variables
| Variable | Description | Default |
|---|---|---|
TRANSPORT |
Transport mode: stdio or sse |
stdio |
HOST |
Host address for SSE transport | 0.0.0.0 |
PORT |
Port number for SSE transport | 8000 |
Examples
stdio Mode (for Claude Desktop)
python server.py
SSE Mode (for HTTP clients)
TRANSPORT=sse PORT=8080 python server.py
Transport Modes
stdio Transport
Use case: Local integrations, Claude Desktop, command-line tools
How it works:
- Server communicates via standard input/output
- Spawned as a subprocess by the MCP client
- No network configuration needed
Configuration example:
{
"mcpServers": {
"multi-tool-server": {
"command": "uv",
"args": ["--directory", "/path/to/project", "run", "server.py"],
"env": {}
}
}
}
SSE Transport
Use case: Remote servers, web applications, HTTP-based clients
How it works:
- Server runs as an HTTP server
- Uses Server-Sent Events for real-time communication
- Accessible via HTTP endpoints
Access URL:
http://localhost:8000/sse
Configuration example:
{
"mcpServers": {
"multi-tool-server": {
"type": "sse",
"url": "http://localhost:8000/sse"
}
}
}
Connecting to Claude Desktop
Step 1: Locate Configuration File
Windows:
%APPDATA%\Claude\claude_desktop_config.json
macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
Linux:
~/.config/Claude/claude_desktop_config.json
Step 2: Get Your Project Path
# Windows PowerShell
Get-Location
# macOS/Linux
pwd
Step 3: Add Server Configuration
Open claude_desktop_config.json and add:
{
"mcpServers": {
"multi-tool-server": {
"command": "uv",
"args": [
"--directory",
"/absolute/path/to/mcp-multi-tool-server",
"run",
"server.py"
],
"env": {
"TRANSPORT": "stdio"
}
}
}
}
Important:
- Use absolute paths (not relative)
- On Windows, use forward slashes
/or escaped backslashes\\ - Replace
/absolute/path/to/mcp-multi-tool-serverwith your actual project path
Step 4: Restart Claude Desktop
Close and reopen Claude Desktop completely. All tools, resources, and prompts should now be available!
API Reference
Calculator Tools
add(a: float, b: float) -> float
Add two numbers together.
Example:
add(2, 3) # Returns: 5.0
subtract(a: float, b: float) -> float
Subtract the second number from the first.
Example:
subtract(10, 4) # Returns: 6.0
multiply(a: float, b: float) -> float
Multiply two numbers.
Example:
multiply(5, 6) # Returns: 30.0
divide(a: float, b: float) -> float
Divide the first number by the second.
Example:
divide(20, 4) # Returns: 5.0
Error: Raises ValueError if divisor is zero.
power(base: float, exponent: float) -> float
Raise a number to a power.
Example:
power(2, 8) # Returns: 256.0
square_root(number: float) -> float
Calculate the square root of a number.
Example:
square_root(16) # Returns: 4.0
Error: Raises ValueError if number is negative.
factorial(n: int) -> int
Calculate the factorial of a non-negative integer.
Example:
factorial(5) # Returns: 120 (5! = 5 × 4 × 3 × 2 × 1)
Error: Raises ValueError if n is negative.
calculate_percentage(part: float, whole: float) -> float
Calculate what percentage one number is of another.
Example:
calculate_percentage(25, 100) # Returns: 25.0 (25%)
Error: Raises ValueError if whole is zero.
Resources
typescript-sdk-mcp://documentation
Returns the full content of the TypeScript SDK MCP documentation markdown file.
Usage: Access this resource through your MCP client to retrieve the documentation.
Prompts
meeting_summary(meeting_date: str, meeting_title: str, transcript: str) -> list[dict]
Generate an executive meeting summary from a transcript.
Parameters:
meeting_date: Date of the meeting (e.g., "2025-01-15")meeting_title: Title of the meetingtranscript: Full meeting transcript text
Returns: A formatted prompt message ready to send to an LLM.
Template:
The prompt uses a template located at templates/meeting_summary/template.md with placeholders:
{{ meeting_date }}{{ meeting_title }}{{ transcript }}
Example Usage:
meeting_summary(
meeting_date="2025-01-15",
meeting_title="Q1 Planning Meeting",
transcript="John: Let's discuss Q1 goals..."
)
Project Structure
mcp-multi-tool-server/
├── .venv/ # Virtual environment
├── templates/
│ └── meeting_summary/
│ └── template.md # Meeting summary prompt template
├── __pycache__/ # Python cache
├── server.py # Main server file
├── pyproject.toml # Project configuration
├── uv.lock # Dependency lock file
├── README.md # This file
├── Typerscript SDK MCP.md # Documentation resource
├── claude_desktop_config.json.example # Example Claude Desktop config
└── .gitignore # Git ignore rules
Testing
Test Calculator Tools
Create a test file test_server.py:
from server import (
add, subtract, multiply, divide,
power, square_root, factorial, calculate_percentage
)
# Test all tools
assert add(2, 3) == 5.0
assert subtract(10, 4) == 6.0
assert multiply(5, 6) == 30.0
assert divide(20, 4) == 5.0
assert power(2, 8) == 256.0
assert square_root(16) == 4.0
assert factorial(5) == 120
assert calculate_percentage(25, 100) == 25.0
print("All tests passed!")
Run:
python test_server.py
Test Resource
from server import get_typescript_sdk_documentation
content = get_typescript_sdk_documentation()
print(content[:100]) # Print first 100 characters
Test Prompt
from server import meeting_summary
result = meeting_summary(
meeting_date="2025-01-15",
meeting_title="Test Meeting",
transcript="This is a test transcript."
)
print(result)
Troubleshooting
Python Not Found
Problem: python --version returns "command not found"
Solution:
- Windows: Reinstall Python with "Add Python to PATH" checked
- macOS/Linux: Use
python3instead ofpython
uv Not Found
Problem: uv --version returns "command not found"
Solution:
- Make sure you opened a new terminal after installation
- Add
~/.cargo/bin(or%USERPROFILE%\.cargo\binon Windows) to PATH - Restart terminal
Virtual Environment Issues
Problem: Can't activate virtual environment
Solution:
- Windows PowerShell:
Set-ExecutionPolicy -ExecutionPolicy RemoteSigned -Scope CurrentUser - Verify
.venvfolder exists:ls .venv(ordir .venvon Windows)
MCP Installation Fails
Problem: uv add "mcp[cli]" fails
Solution:
- Ensure virtual environment is activated (you should see
(.venv)in prompt) - Update uv:
uv self update - Check Python version:
python --version(should be 3.10+)
Server Won't Start
Problem: Server fails to start
Solution:
- Verify virtual environment is activated
- Check MCP is installed:
uv pip list | grep mcp - Ensure
server.pyexists in current directory
Claude Desktop Connection Issues
Problem: Server doesn't appear in Claude Desktop
Solution:
- Verify configuration file path is correct
- Use absolute paths (not relative)
- Check JSON syntax is valid
- Ensure
uvis in PATH or use full path - Restart Claude Desktop completely
- Check Claude Desktop logs for errors
SSE Transport Issues
Problem: SSE server won't start
Solution:
- Check if port is already in use:
lsof -i :8000(macOS/Linux) ornetstat -ano | findstr :8000(Windows) - Try a different port:
PORT=8080 TRANSPORT=sse python server.py - Ensure firewall allows connections on the specified port
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
- Fork the repository
- Create your feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
License
This project is provided as-is for educational and personal use.
Additional Resources
Support
If you encounter any issues or have questions:
- Check the Troubleshooting section
- Search existing GitHub Issues
- Create a new issue with:
- Description of the problem
- Steps to reproduce
- Expected vs actual behavior
- System information (OS, Python version, etc.)
Made with ❤️ using FastMCP and the Model Context Protocol
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.