AI agents call get_test_findings_counts to retrieve information from SafeBreach MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_' prefix and context among similar query/retrieval tools strongly suggest this tool retrieves data about test findings counts without modifying state. The empty description prevents higher confidence, but the naming pattern and sibling tools provide sufficient evidence for Read classification with low severity impact.
From the tool's definition Tool name 'get_test_findings_counts' begins with 'get_', indicating a retrieval operation. The method is grouped with other read-only tools like 'get_all_studio_attacks', 'get_console_simulators', and 'get_full_simulation_logs'.
Documented attack patterns abuse exactly the kind of access get_test_findings_counts gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SafeBreach MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_test_findings_counts:
{
"version": "1",
"default": "deny",
"tools": {
"get_test_findings_counts": {}
}
}get_test_findings_counts 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.
get_test_findings_counts. It is categorised as a Read tool in the SafeBreach MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SafeBreach MCP Server MCP server in PolicyLayer and add a rule for get_test_findings_counts: 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 SafeBreach MCP Server. Nothing to install.
get_test_findings_counts 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 get_test_findings_counts 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 get_test_findings_counts. 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.
get_test_findings_counts is provided by the SafeBreach MCP Server MCP server (safebreach/safebreach-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SafeBreach 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.
35 SafeBreach MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.