AI agents call search_all_repositories 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.
The tool name strongly suggests a search operation across repositories, which is a read-only retrieval action. The pattern of sibling tools on the same server that provide package queries (get_aur_info, get_package_info, get_mirrorlist) without modifying state supports classification as Read.
From the tool's definition Tool name 'search_all_repositories' indicates it queries package repositories. No description provided, but context from sibling tools (get_aur_info, get_package_info, get_mirrorlist, get_pacman_log) all being Read operations suggests this is a search/query…
Attacks that exploit this kind of access
search_all_repositories. 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 search_all_repositories: 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.
search_all_repositories 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 search_all_repositories 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 search_all_repositories. 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.
search_all_repositories 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 →