Safe Local Python Executor is an MCP server that provides a secure environment for running Python code generated by LLMs. It uses Hugging Face's LocalPythonExecutor
to create a basic isolation layer, allowing you to execute Python code locally without the overhead of Docker or VMs, while still maintaining security.
The executor offers several security features:
This approach balances convenience with security, providing better protection than direct eval()
while being easier to set up than Docker containers or VMs.
The simplest way to install for Claude Desktop:
npx -y @smithery/cli install @maxim-saplin/mcp_safe_local_python_executor --client claude
If you prefer to install manually:
Install uv
first:
# On macOS
brew install uv
# For other platforms, check the official docs
# https://docs.astral.sh/uv/getting-started/installation/
Clone the repository and run:
git clone https://github.com/your-username/mcp_safe_local_python_executor.git
cd mcp_safe_local_python_executor
uv run mcp_server.py
Install Claude Desktop from claude.ai
Edit the configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
Add this configuration (update the path to your actual installation):
{
"mcpServers": {
"safe-local-python-executor": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp_local_python_executor/",
"run",
"mcp_server.py"
]
}
}
}
You can ask Claude to perform Python operations like:
Claude will use the safe Python executor to run the code and return the results.
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "safe-local-python-executor" '{"command":"uv","args":["--directory","/path/to/mcp_local_python_executor/","run","mcp_server.py"]}'
See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"safe-local-python-executor": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp_local_python_executor/",
"run",
"mcp_server.py"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
~/.config/Claude/claude_desktop_config.json
2. Add this to your configuration file:
{
"mcpServers": {
"safe-local-python-executor": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp_local_python_executor/",
"run",
"mcp_server.py"
]
}
}
}
3. Restart Claude Desktop for the changes to take effect