Microsandbox MCP
Self-hosted platform for secure execution of AI-generated code, exposed via MCP.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Microsandbox MCP, derived from its capabilities.
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
A self-hosted sandbox platform for securely executing AI code, aimed at code-interpreter, data-analysis, and browser-use workloads. It isolates untrusted model-generated code from the host, reducing the code-execution risk category while still running arbitrary code inside the sandbox.
Key features
- Self-hosted secure execution
- Code interpreter and data analysis
- Browser-use support
Use cases
- Self-hosted code interpreter for agents
- Sandboxed data analysis pipelines