List all known categories of knowledge (people, projects, topics, etc.) with thought counts. Use this to discover what the brain contains before searching, or to orient yourself in an unfamiliar brain.
AI agents call list_dimensions 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 performs a read-only query to discover and enumerate existing dimensions (categories) within the semantic memory system. It has no side effects, does not modify data, and cannot cause harm through misuse. The worst case is information disclosure about what topics/categories exist in the knowledge base, which is low severity.
From the tool's definition Tool name is 'list_dimensions' and description states it 'List all known categories of knowledge' and provides 'thought counts' - these are retrieval operations with no modification or deletion of data.
Attacks that exploit this kind of access
List all known categories of knowledge (people, projects, topics, etc.) with thought counts. Use this to discover what the brain contains before searching, or to orient yourself in an unfamiliar brain. 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_dimensions: 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_dimensions 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_dimensions 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_dimensions. 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_dimensions 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 →