AI agents call get_package_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 retrieves package metadata from either the repository or local installation database. The pacman flags -Si and -Qi are non-destructive information queries. There are no side effects, no code execution, no data modification, and no system state changes. This is a straightforward Read operation with minimal risk when misused by an AI agent.
From the tool's definition Tool name 'get_package_info' and description 'Detailed info for a package (repo via -Si, else installed via -Qi)' indicate query-only operations using pacman's -Si (sync info) and -Qi (query info) flags, both of which retrieve metadata without modification.
Attacks that exploit this kind of access
Detailed info for a package (repo via -Si, else installed via -Qi). 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_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_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_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_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_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 →