tool_install · Lockstep MCP: Risk & Policy

WHAT IT DOES

What tool_install does on Lockstep

AI agents invoke tool_install to trigger actions in Lockstep. 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 tool_install needs a policy

Installing packages via a package manager executes system-level commands and introduces new software into the environment. This goes beyond a simple write (it runs external processes, modifies system state, and can introduce arbitrary code). An AI agent misusing this could install malicious packages or destabilize the environment, making it high severity.

From the tool's definition 'Install a tool using a package manager' — this triggers an external operation (package manager execution) that installs software onto the system

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tool_install Rate-limited

tool_install 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": {
    "tool_install": {
      "limits": [
        {
          "counter": "tool_install_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 Lockstep, so you can run agents against it safely.

FAQ

Questions about tool_install

What does the tool_install tool do? +

Install a tool using a package manager. It is categorised as a Execute tool in the Lockstep MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on tool_install? +

Register the Lockstep MCP server in PolicyLayer and add a rule for tool_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 Lockstep. Nothing to install.

What risk level is tool_install? +

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

Can I rate-limit tool_install? +

Yes. Add a rate_limit block to the tool_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 tool_install completely? +

Set action: deny in the PolicyLayer policy for tool_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 tool_install? +

tool_install is provided by the Lockstep MCP server (tmmoore286/lockstep-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.