Microsandbox MCP

MCP Tools and AgentsFreeOpen Source

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.

AIVSS 5.7 · Medium

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