Code Interpreter
Adds secure code execution capabilities to Claude Desktop using E2B Sandbox, supporting both JavaScript and Python environments.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Code Interpreter, 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
MCP server that runs agent-generated code inside E2B's secure cloud sandboxes. It executes arbitrary code in isolated microVMs, which is the central capability and the central risk (sandbox escape, resource abuse).
Key features
- Run arbitrary code in a sandbox
- Isolated cloud microVMs
- Stdout/stderr capture
Use cases
- Safe code execution for agents
- Data-analysis scripting