AI agents call what_do_i_think 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 appears to query the user's indexed conversation history and cognitive patterns to retrieve stored thoughts or beliefs. No side effects, modifications, deletions, code execution, or financial operations are implied. It is a read-only retrieval operation over indexed historical data.
From the tool's definition Tool name 'what_do_i_think' and sibling tools like 'bob_search', 'bob_thinking_trajectory', 'bob_tunnel_state' indicate this retrieves or queries stored conversation history and cognitive state from indexed embeddings.
Documented attack patterns abuse exactly the kind of access what_do_i_think 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 what_do_i_think:
{
"version": "1",
"default": "deny",
"tools": {
"what_do_i_think": {}
}
}what_do_i_think 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.
what_do_i_think. 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 what_do_i_think: 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.
what_do_i_think 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 what_do_i_think 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 what_do_i_think. 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.
what_do_i_think 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.