MCP Terminal Server

A secure terminal execution server implementing the Model Context Protocol (MCP). This server provides controlled command execution capabilities with security features and resource limits.

Features

Command Execution: Execute shell commands with output capture and error handling
Security Controls: Restrict allowed commands and prevent command injection
Resource Controls:
- Command timeouts
- Maximum output size limits
MCP Protocol Support:
- Standard MCP message format
- Capability advertisement
- Streaming output support

Development

Local Setup

# Clone the repository
git clone https://github.com/RinardNick/mcp-terminal.git
cd mcp-terminal

# Create and activate virtual environment using uv
uv venv
source .venv/bin/activate  # or .venv\Scripts\activate on Windows

# Install development dependencies
uv pip install -e ".[dev]"

Publishing to PyPI

# Build the package
uv pip install build
python -m build

# Upload to PyPI
uv pip install twine
python -m twine upload dist/*

Testing with MCP Inspector

The MCP Inspector tool can be used to test the server implementation:

# Install inspector
npm install -g @modelcontextprotocol/inspector

# Test server
npx @modelcontextprotocol/inspector python3 src/mcp_terminal/server.py --allowed-commands "python,pip,git,ls,cd"

Running Tests

# Run all tests
pytest tests/

# Run specific test file
pytest tests/test_terminal.py

# Run with coverage
pytest --cov=mcp_terminal tests/

Using with Claude Desktop

Once the package is published to PyPI:

Install UV (if not already installed):
```
pip install uv
```
Install the Package using UV:
```
uv pip install mcp-terminal
```

Configure Claude Desktop: Edit your Claude Desktop config file (typically at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "terminal": {
      "command": "uv",
      "args": [
        "pip",
        "run",
        "mcp-terminal",
        "--allowed-commands",
        "python,pip,git,ls,cd",
        "--timeout-ms",
        "30000",
        "--max-output-size",
        "1048576"
      ]
    }
  }
}

Protocol Implementation

The server implements the Model Context Protocol (MCP) with the following capabilities:

Capabilities Advertisement

{
  "protocol": "1.0.0",
  "name": "terminal",
  "version": "1.1.0",
  "capabilities": {
    "execute": {
      "description": "Execute a terminal command",
      "parameters": {
        "command": {
          "type": "string",
          "description": "The command to execute"
        }
      },
      "returns": {
        "type": "object",
        "properties": {
          "exitCode": { "type": "number" },
          "stdout": { "type": "string" },
          "stderr": { "type": "string" },
          "startTime": { "type": "string" },
          "endTime": { "type": "string" }
        }
      }
    }
  }
}

Message Format

Request:

{
  "type": "execute",
  "data": {
    "command": "echo 'hello world'"
  }
}

Response:

{
  "type": "result",
  "data": {
    "command": "echo 'hello world'",
    "exitCode": 0,
    "stdout": "hello world\n",
    "stderr": "",
    "startTime": "2024-01-20T12:34:56.789Z",
    "endTime": "2024-01-20T12:34:56.790Z"
  }
}

Error:

{
  "type": "error",
  "data": {
    "message": "command not allowed"
  }
}

Security Considerations

Command Validation:
- Only allowed commands can be executed
- Shell operators are blocked
- Command injection attempts are prevented
Resource Protection:
- Command timeouts prevent hanging
- Output size limits prevent memory exhaustion
- Error handling for all failure cases
Best Practices:
- Always set allowed-commands in production
- Use conservative timeout and size limits
- Monitor command execution logs

Contributing

Fork the repository
Create your feature branch (git checkout -b feature/amazing-feature)
Commit your changes (git commit -m 'Add some amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.