Unified search across the brain: memory, facts, recipes, personal contacts, bucket list, trips, and documents. Returns top-N relevant rows per source — the LLM synthesizes the final answer. Use this for
AI agents call ask_brain to retrieve information from Personal Brain without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a retrieval/query tool with no side effects, fitting the Read category. However, severity is high because it provides broad access to sensitive personal data across 8 information domains (memories, contacts, health-adjacent facts, personal documents, etc.), creating significant privacy and security risks if an AI agent misuses the search to extract private information without authorization.
From the tool's definition Tool performs 'unified search across the brain: memory, facts, recipes, personal contacts, bucket list, trips, and documents' with no modification or deletion capability. Returns query results for LLM synthesis.
Attacks that exploit this kind of access
Unified search across the brain: memory, facts, recipes, personal contacts, bucket list, trips, and documents. Returns top-N relevant rows per source — the LLM synthesizes the final answer. Use this for. It is categorised as a Read tool in the Personal Brain MCP Server, which means it retrieves data without modifying state.
Register the Personal Brain MCP server in PolicyLayer and add a rule for ask_brain: 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 Personal Brain. Nothing to install.
ask_brain 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 ask_brain 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 ask_brain. 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.
ask_brain is provided by the Personal Brain MCP server (phantomts/personal-brain-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →