coderunner
pipStandardCoderunner provides a secure local sandbox for executing LLM-generated code using Apple containers. It exposes APIs to run, test, and debug Python code in isolated environments. Connects to local Mac systems and integrates with LLMs for code generation. Useful for developers testing AI-generated code, ensuring security and isolation.
802300Updated 4 days ago
Overview
Coderunner provides a secure local sandbox for executing LLM-generated code using Apple containers. It exposes APIs to run, test, and debug Python code in isolated environments. Connects to local Mac systems and integrates with LLMs for code generation. Useful for developers testing AI-generated code, ensuring security and isolation.
Installation
1Install the package
pip
pip install coderunner2Add to Claude
Add this configuration to your claude_desktop_config.json:
claude_desktop_config.json
{
"mcpServers": {
"instavm-coderunner-github": {
"command": "uvx",
"args": [
"pip install coderunner"
]
}
}
}3Verify installation
Restart Claude Desktop, then ask:
"What tools do you have available from coderunner?"
Prerequisites
- Python 3.10 or higher
- pip or uv package manager
- Claude Desktop or Claude API access
Configuration
No configuration required. This server works out of the box.
Usage Examples
List Resources
"What resources are available in coderunner?"
Claude will query available resources and return a list of what you can access.
Get Details
"Show me details about [specific item] in coderunner"
Claude will fetch and display detailed information about the requested item.
Create New
"Create a new [item] in coderunner with [details]"
Claude will use the appropriate tool to create the resource and confirm success.
Works with coderunner
Related skills
Browse all skillsNeed help with MCP integration?
We build custom MCP integrations for B2B companies. From simple connections to complex multi-tool setups.