Recommend documentation packs, skills, and optional MCPs for this repo based on its package metadata. Recommendations never install anything automatically.
AI agents call kage_registry_recommend to retrieve information from Kage without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool only reads package metadata and returns recommendations. It explicitly states it never installs anything automatically, confirming there are no side effects. This is a pure read/query operation with minimal blast radius.
From the tool's definition Recommend documentation packs, skills, and optional MCPs for this repo based on its package metadata. Recommendations never install anything automatically.
Documented attack patterns abuse exactly the kind of access kage_registry_recommend gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kage, and nothing reaches the server without passing your rules. This is the rule we recommend for kage_registry_recommend:
{
"version": "1",
"default": "deny",
"tools": {
"kage_registry_recommend": {}
}
}kage_registry_recommend is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Recommend documentation packs, skills, and optional MCPs for this repo based on its package metadata. Recommendations never install anything automatically. It is categorised as a Read tool in the Kage MCP Server, which means it retrieves data without modifying state.
Register the Kage MCP server in PolicyLayer and add a rule for kage_registry_recommend: 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 Kage. Nothing to install.
kage_registry_recommend 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 kage_registry_recommend 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 kage_registry_recommend. 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.
kage_registry_recommend is provided by the Kage MCP server (@kage-core/kage-graph-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kage, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
62 Kage tools catalogued and risk-classified — across an index of 43,000+ MCP servers.