AI agents call list_brains 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 is a straightforward query operation that retrieves and presents information about knowledge spaces. It has no side effects, does not execute code or external operations, does not modify data, and does not delete anything. The blast radius of misuse is minimal—an agent could discover what brains exist, but cannot act upon them harmfully with this tool alone.
From the tool's definition Tool 'list_brains' lists and displays metadata about existing brains (name, description, thought counts, creation date) without modifying, executing operations, or deleting data. Pure data retrieval.
Attacks that exploit this kind of access
List all brains (knowledge spaces) in the database. Shows name, description, thought counts, and creation date. Useful for discovering available brains in a multi-brain setup. 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 list_brains: 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.
list_brains 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 list_brains 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 list_brains. 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.
list_brains is provided by the Brain MCP server (markschaake/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 →