Search debug history for past solutions. AUTO-call silently on errors.
AI agents call debug_search to retrieve information from MCP Creator Growth without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries historical debugging data without modifying, deleting, or executing anything. Even though it auto-triggers on errors, it only retrieves information. The most severe risk is information disclosure of past debug records, which is a low-severity read concern since the data is already part of the user's own learning history.
From the tool's definition Tool name is 'debug_search' and description states it 'Search[es] debug history for past solutions', which is a retrieval operation with no side effects. The AUTO-call behavior on errors is a read-only fallback mechanism.
Documented attack patterns abuse exactly the kind of access debug_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Creator Growth, and nothing reaches the server without passing your rules. This is the rule we recommend for debug_search:
{
"version": "1",
"default": "deny",
"tools": {
"debug_search": {}
}
}debug_search 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 debug history for past solutions. AUTO-call silently on errors. It is categorised as a Read tool in the MCP Creator Growth MCP Server, which means it retrieves data without modifying state.
Register the MCP Creator Growth MCP server in PolicyLayer and add a rule for debug_search: 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 MCP Creator Growth. Nothing to install.
debug_search 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 debug_search 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 debug_search. 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.
debug_search is provided by the MCP Creator Growth MCP server (sunflowerslwtech/mcp_creator_growth). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Creator Growth, 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.
4 MCP Creator Growth tools catalogued and risk-classified — across an index of 43,000+ MCP servers.