lpm_install · Lpm Registry MCP: Risk & Policy

WHAT IT DOES

What lpm_install does on Lpm Registry

AI agents use lpm_install to create or update resources in Lpm Registry — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lpm Registry environment.

WHY IT NEEDS A POLICY

Why lpm_install needs a policy

Installing packages modifies the project state by adding dependencies to configuration files and package directories. While this is technically reversible (packages can be uninstalled/removed), it has significant side effects including code execution during installation scripts, transitive dependency chain modifications, and potential security risks from third-party code.

From the tool's definition The tool performs 'Install an LPM package as a managed dependency' which modifies project configuration files ('Package.swift via SE-0292') and dependency trees ('node_modules').

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

lpm_install Rate-limited

lpm_install stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "lpm_install": {
      "limits": [
        {
          "counter": "lpm_install_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about lpm_install

What does the lpm_install tool do? +

Install an LPM package as a managed dependency. JS packages go to node_modules (like npm install), Swift packages edit Package.swift via SE-0292. Use for libraries, utilities, and SDKs. Requires LPM CLI installed. It is categorised as a Write tool in the Lpm Registry MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on lpm_install? +

Register the Lpm Registry MCP server in PolicyLayer and add a rule for lpm_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 Lpm Registry. Nothing to install.

What risk level is lpm_install? +

lpm_install is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit lpm_install? +

Yes. Add a rate_limit block to the lpm_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.

How do I block lpm_install completely? +

Set action: deny in the PolicyLayer policy for lpm_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.

What MCP server provides lpm_install? +

lpm_install is provided by the Lpm Registry MCP server (lpm-dev/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.