Enables execution of TypeScript code to call MCP tools instead of direct tool calls, reducing token usage by up to 98% while orchestrating complex multi-tool workflows through secure sandboxed code execution.
Enables Claude Code to perform programmatic tool calling by executing Python scripts that interact with multiple MCP servers in a single round-trip. This reduces latency and token consumption by keeping intermediate tool results within the local Python runtime instead of the conversation context.
Runs AI-generated code in secure Firecracker microVMs with opt-in network policy enforcement, PII scanning, prompt injection defense, and audit logging. Exposes MCP tools for running commands, managing files, and the full sandbox lifecycle.
Executes Python code in isolated rootless containers while proxying MCP server tools, reducing context overhead by 95%+ and enabling complex multi-tool workflows through sandboxed code execution.