install_package · AgentExecMPC MCP: Risk & Policy

WHAT IT DOES

What install_package does on AgentExecMPC

AI agents invoke install_package to trigger actions in AgentExecMPC. 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_package needs a policy

Installing packages modifies the runtime environment by fetching and executing external code, which can introduce malicious dependencies, alter system behavior, or create persistent changes. This is an Execute-level action (running external code/scripts as part of installation) with high severity since misuse could compromise the container environment or supply chain.

From the tool's definition Tool name 'install_package' on a server described as enabling agents to 'execute shell commands, run code, and install packages' in Docker. Description is empty, so classification relies on name and server context.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

install_package Rate-limited

install_package 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_package": {
      "limits": [
        {
          "counter": "install_package_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 AgentExecMPC, so you can run agents against it safely.

FAQ

Questions about install_package

What does the install_package tool do? +

install_package. It is categorised as a Execute tool in the AgentExecMPC 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_package? +

Register the AgentExecMPC MCP server in PolicyLayer and add a rule for install_package: 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 AgentExecMPC. Nothing to install.

What risk level is install_package? +

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

Can I rate-limit install_package? +

Yes. Add a rate_limit block to the install_package 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_package completely? +

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

install_package is provided by the AgentExecMPC MCP server (realugbun/agentexecmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.