ForeverVM MCP
MCP server to run Python in a persistent code sandbox.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for ForeverVM MCP, derived from its capabilities.
AIVSS 6.4 · Medium
View MAESTRO 7-layer threat model →These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology. Are you the vendor? Factual corrections are free.
Overview
Provides a code sandbox to run Python for agents, with persistent VMs. It exists to contain the arbitrary-code-execution risk of letting a model run code, though it still executes untrusted output; sandbox egress and resource limits are the relevant controls.
Key features
- Python code sandbox
- Persistent VMs
- Safe execution for agents
Use cases
- Sandboxed Python for agents
- Stateful code interpreter sessions