cli_cache_update · LaunchFrame MCP: Risk & Policy

WHAT IT DOES

What cli_cache_update does on LaunchFrame MCP

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

WHY IT NEEDS A POLICY

Why cli_cache_update needs a policy

This tool modifies cached service data on the local system by force-updating it, which is a reversible write operation. It does not execute arbitrary commands, delete data irreversibly, or move money. While it affects local state, the changes are non-destructive and can be reverted by re-caching.

From the tool's definition Tool name 'cli_cache_update' and description 'Force-update the local LaunchFrame service cache by re-downloading cached services' indicates modification of cached data through re-downloading and updating operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cli_cache_update Rate-limited

cli_cache_update 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": {
    "cli_cache_update": {
      "limits": [
        {
          "counter": "cli_cache_update_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 LaunchFrame MCP, so you can run agents against it safely.

FAQ

Questions about cli_cache_update

What does the cli_cache_update tool do? +

Force-update the local LaunchFrame service cache by re-downloading cached services. It is categorised as a Write tool in the LaunchFrame MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on cli_cache_update? +

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

What risk level is cli_cache_update? +

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

Can I rate-limit cli_cache_update? +

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

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

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