View or modify your household shopping list. action=
AI agents use shopping_list to create or update resources in Personal Brain — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Personal Brain environment.
The tool explicitly supports both reading and modifying a shopping list. Since it can alter data (add/remove items), it falls under Write. The blast radius is medium — misuse could corrupt personal shopping data, but effects are reversible and limited in scope.
From the tool's definition 'View or modify your household shopping list' — the modify capability makes this a Write tool
Attacks that exploit this kind of access
View or modify your household shopping list. action=. It is categorised as a Write tool in the Personal Brain MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Personal Brain MCP server in PolicyLayer and add a rule for shopping_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 Personal Brain. Nothing to install.
shopping_list is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the shopping_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 shopping_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.
shopping_list 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 →