Install a Node.js version using NVM.
AI agents invoke nvm_install to trigger actions in NVM MCP Server. 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.
Installing a Node.js version triggers an external operation that downloads and installs software onto the system. This is more than a simple write — it executes NVM commands and modifies the system environment by adding a new Node.js runtime. The blast radius is medium as it could install unexpected or malicious Node versions if misused.
From the tool's definition Install a Node.js version using NVM
Attacks that exploit this kind of access
Install a Node.js version using NVM. It is categorised as a Execute tool in the NVM MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the NVM MCP Server MCP server in PolicyLayer and add a rule for nvm_install: 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 NVM MCP Server. Nothing to install.
nvm_install 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 nvm_install 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 nvm_install. 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.
nvm_install is provided by the NVM MCP Server MCP server (realjacoblinder/nvm-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 →