AI agents call get_package_cache_info to retrieve information from Cachyos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries information about the pacman package cache—specifically its size and file count—to help identify cleanup candidates. It performs a read-only inspection of existing cache state without creating, modifying, deleting, or executing anything. The tool has minimal blast radius even if misused by an AI agent, as it only retrieves informational data.
From the tool's definition Tool name 'get_package_cache_info' and description 'Size & file count of the pacman package cache' indicate retrieval of cache metadata with no modification of system state.
Attacks that exploit this kind of access
Size & file count of the pacman package cache (cleanup candidate). It is categorised as a Read tool in the Cachyos MCP Server, which means it retrieves data without modifying state.
Register the Cachyos MCP server in PolicyLayer and add a rule for get_package_cache_info: 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 Cachyos. Nothing to install.
get_package_cache_info is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_package_cache_info 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.
Set action: deny in the PolicyLayer policy for get_package_cache_info. 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.
get_package_cache_info is provided by the Cachyos MCP server (raindancer118/cachyos-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →