AI agents call explore_dimension 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 retrieves and queries existing semantic memory data without modifying, deleting, or executing any operations. It is purely informational access to persistent knowledge storage, making it a Read category risk. Severity is low because retrieval of knowledge poses minimal security risk unless the database contains highly sensitive information, but the tool itself performs no destructive or operational actions.
From the tool's definition Tool description explicitly states 'Retrieve all knowledge linked to a specific person, project, topic, or other dimension.' The verb 'retrieve' and the context of querying stored thoughts via vector embeddings indicates a read-only query operation with no…
Attacks that exploit this kind of access
Retrieve all knowledge linked to a specific person, project, topic, or other dimension. Use this when the user asks about a particular subject and you want everything the brain knows about it. 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 explore_dimension: 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.
explore_dimension 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 explore_dimension 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 explore_dimension. 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.
explore_dimension 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 →