install_dependencies · Build MCP Server MCP: Risk & Policy

WHAT IT DOES

What install_dependencies does on Build MCP Server

AI agents invoke install_dependencies to trigger actions in Build 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.

WHY IT NEEDS A POLICY

Why install_dependencies needs a policy

Installing dependencies executes package manager commands (npm/yarn/pnpm install) which run arbitrary lifecycle scripts from third-party packages, modify the filesystem (node_modules, lock files), and can execute code supplied by external packages. This goes beyond a simple Write because it triggers external operations and code execution.

From the tool's definition Install project dependencies — installs packages from external sources, runs lifecycle scripts (preinstall, postinstall, install), and modifies node_modules and lock files

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

install_dependencies Rate-limited

install_dependencies 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": {
    "install_dependencies": {
      "limits": [
        {
          "counter": "install_dependencies_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Build MCP Server, so you can run agents against it safely.

FAQ

Questions about install_dependencies

What does the install_dependencies tool do? +

Install project dependencies. It is categorised as a Execute tool in the Build 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 install_dependencies? +

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

What risk level is install_dependencies? +

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

Can I rate-limit install_dependencies? +

Yes. Add a rate_limit block to the install_dependencies 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 install_dependencies completely? +

Set action: deny in the PolicyLayer policy for install_dependencies. 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 install_dependencies? +

install_dependencies is provided by the Build MCP Server MCP server (teodortrotea/mcptest). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.