npm_command

Run npm commands (install, test, build, etc)

SERVERCode MCP Server SOURCEagentics-ai/code-mcp

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/agentics-ai-code-mcp/npm-command.md

WHAT IT DOES

What npm_command does on Code MCP Server

AI agents invoke npm_command to trigger actions in Code 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.

RISK

Why npm_command is rated High

npm commands trigger external operations whose effects depend on arguments. While 'test' and 'build' are relatively contained, 'install' modifies the project state by downloading and integrating dependencies. More critically, npm scripts can execute arbitrary shell commands defined in package.json, making this a code execution tool.

From the tool's definition Tool description states 'Run npm commands' which are executable operations. npm commands can install packages (modifying dependencies), run scripts (arbitrary code execution), and build projects.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs npm_command safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Code MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For npm_command, this is the rule to start with:

npm_command Rate-limited

npm_command stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "npm_command": {
      "limits": [
        {
          "counter": "npm_command_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Code MCP Server, apply this rule, and every npm_command call is checked against it from then on.

FAQ

Questions about npm_command

What does the npm_command tool do? +

Run npm commands (install, test, build, etc). It is categorised as a Execute tool in the Code MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on npm_command? +

Register the Code MCP Server MCP server in PolicyLayer and add a rule for npm_command: 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 Code MCP Server. Nothing to install.

What risk level is npm_command? +

npm_command is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit npm_command? +

Yes. Add a rate_limit block to the npm_command 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.

How do I block npm_command completely? +

Set action: deny in the PolicyLayer policy for npm_command. 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.

What MCP server provides npm_command? +

npm_command is provided by the Code MCP Server MCP server (agentics-ai/code-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Code MCP Server, and thousands of servers like it.

This server

All 73 Code MCP Server tools → High-risk tools on this server →

Across the catalogue

adb_shell_command on Android Forensics ADB MCP Server → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →