Inspect what L1 filtered out. Optional reason filter (e.g. 'cc:build-log-paste').
AI agents call bob_dropped to retrieve information from Brain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and returns data about items that were dropped/filtered by L1 processing. It has no side effects, only inspects stored filtering results. The optional 'reason' filter further confirms a query/retrieval pattern. Severity is low as it only exposes internal filtering metadata.
From the tool's definition 'Inspect what L1 filtered out' — retrieves/queries filtered-out items, with optional reason filter parameter
Documented attack patterns abuse exactly the kind of access bob_dropped gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Brain, and nothing reaches the server without passing your rules. This is the rule we recommend for bob_dropped:
{
"version": "1",
"default": "deny",
"tools": {
"bob_dropped": {}
}
}bob_dropped 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.
Inspect what L1 filtered out. Optional reason filter (e.g. 'cc:build-log-paste'). It is categorised as a Read tool in the Brain MCP Server, which means it retrieves data without modifying state.
Register the Brain MCP server in PolicyLayer and add a rule for bob_dropped: 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 Brain. Nothing to install.
bob_dropped 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 bob_dropped 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 bob_dropped. 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.
bob_dropped is provided by the Brain MCP server (mordechaipotash/brain-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Brain, 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.
34 Brain tools catalogued and risk-classified — across an index of 43,000+ MCP servers.