Install npm dependencies and run JavaScript code inside a running sandbox container. After running, you must manually stop the sandbox to free resources. The code must be valid ESModules (import/export syntax). Best for complex workflows where you want to reuse the environment across multiple exe...
AI agents invoke run_js to trigger actions in Node Code Sandbox MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool allows an AI agent to execute arbitrary JavaScript code in a sandbox environment with npm package installation capabilities. While sandboxed, the blast radius is high because: (1) arbitrary JS execution can access file systems, network, and environment variables within the sandbox; (2) npm package installation can introduce malicious dependencies; (3) the agent controls what code runs and what packages are…
From the tool's definition Tool description explicitly states it can "run JavaScript code inside a running sandbox container" and "Install npm dependencies". The name "run_js" combined with the capability to execute arbitrary code dynamically is indicative of code execution.
Attacks that exploit this kind of access
Install npm dependencies and run JavaScript code inside a running sandbox container. After running, you must manually stop the sandbox to free resources. The code must be valid ESModules (import/export syntax). Best for complex workflows where you want to reuse the environment across multiple executions. When reading and writing from the Node.js processes, you always need to read from and write to the. It is categorised as a Execute tool in the Node Code Sandbox MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Node Code Sandbox MCP server in PolicyLayer and add a rule for run_js: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Node Code Sandbox MCP. Nothing to install.
run_js is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run_js rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for run_js. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
run_js is provided by the Node Code Sandbox MCP server (mozicim/node-code-sandbox-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →