YepCode MCP Server
MCP server to execute LLM-generated code in a secure, scalable sandbox and build custom MCP tools.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for YepCode MCP Server, derived from its capabilities.
AIVSS 7.1 · High
View MAESTRO 7-layer threat model →Overview
Runs any LLM-generated JavaScript or Python code in YepCode's secure, scalable sandbox with full NPM/PyPI support, and lets you turn code into custom MCP tools. It is both a mitigation (sandboxed execution) and a surface (it executes untrusted model code and can install packages), so package-supply-chain and egress controls matter.
Key features
- Sandboxed code execution
- NPM/PyPI package support
- Build custom MCP tools
Use cases
- Running agent-generated code safely
- Turning scripts into MCP tools