Overview of the whole second brain: note count, categories, recent titles, journal days.
AI agents call brain_list to retrieve information from Claude Team MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and displays aggregated information about a knowledge management system (the 'second brain'). It retrieves note counts, categories, titles, and journal history—all read-only operations that do not modify data, execute code, delete records, or trigger financial transactions. The blast radius of misuse is minimal, as an AI agent querying this information cannot cause harm through reading alone.
From the tool's definition Tool name 'brain_list' and description 'Overview of the whole second brain: note count, categories, recent titles, journal days' indicate retrieval of metadata and summaries about stored information without modification, deletion, or execution of external…
Attacks that exploit this kind of access
Overview of the whole second brain: note count, categories, recent titles, journal days. It is categorised as a Read tool in the Claude Team MCP MCP Server, which means it retrieves data without modifying state.
Register the Claude Team MCP server in PolicyLayer and add a rule for brain_list: 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 Claude Team MCP. Nothing to install.
brain_list 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 brain_list 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 brain_list. 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.
brain_list is provided by the Claude Team MCP server (lakshan12367/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 →