AI agents call search_tools to retrieve information from Code Mode Toon without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the name alone, 'search_tools' appears to retrieve or list available tools without modifying state. The incomplete description reduces confidence, but the naming pattern suggests a read-only operation consistent with sibling tools like 'list_servers' and 'list_workflows'. No indicators of write, execute, destructive, or financial operations are evident.
From the tool's definition Tool name is 'search_tools' which indicates a query/search operation. Description is incomplete ('USE WHEN you don') and uninformative, providing no details about side effects or scope.
Documented attack patterns abuse exactly the kind of access search_tools gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Code Mode Toon, and nothing reaches the server without passing your rules. This is the rule we recommend for search_tools:
{
"version": "1",
"default": "deny",
"tools": {
"search_tools": {}
}
}search_tools 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.
USE WHEN you don. It is categorised as a Read tool in the Code Mode Toon MCP Server, which means it retrieves data without modifying state.
Register the Code Mode Toon MCP server in PolicyLayer and add a rule for search_tools: 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 Code Mode Toon. Nothing to install.
search_tools 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_tools 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_tools. 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_tools is provided by the Code Mode Toon MCP server (ziad-hsn/code-mode-toon). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Code Mode Toon, 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.
8 Code Mode Toon tools catalogued and risk-classified — across an index of 43,000+ MCP servers.