AI agents call search_styles to retrieve information from Krea MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search/query action to discover and list available styling options. It does not create, modify, delete, execute arbitrary operations, move funds, or cause irreversible changes. The blast radius of misuse is minimal—an agent might request excessive searches or inappropriate styles, but cannot generate unauthorized content, delete data, or cause financial harm through this tool alone.
From the tool's definition Tool description states it 'Search[es] for styles/LoRAs' — a query operation that retrieves available style options for use in image generation with no side effects or data modification.
Documented attack patterns abuse exactly the kind of access search_styles gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Krea MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_styles:
{
"version": "1",
"default": "deny",
"tools": {
"search_styles": {}
}
} search_styles 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.
Search for styles/LoRAs to use in image generation. It is categorised as a Read tool in the Krea MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Krea MCP Server MCP server in PolicyLayer and add a rule for search_styles: 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 Krea MCP Server. Nothing to install.
search_styles 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_styles 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_styles. 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_styles is provided by the Krea MCP Server MCP server (keugenek/krea-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Krea MCP Server, 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.
9 Krea MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.