Check pantry contents, add items, mark items consumed, or list what
AI agents use pantry 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 pantry tool performs reversible write operations (adding items, marking consumption) that modify the user's personal food inventory. While the changes are non-destructive and recoverable, they alter stored state. This is primarily a Write category tool.
From the tool's definition Tool supports 'add items' and 'mark items consumed' — state-changing operations on pantry data. Description confirms modification capabilities: 'add items, mark items consumed'.
Attacks that exploit this kind of access
Check pantry contents, add items, mark items consumed, or list what. 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 pantry: 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.
pantry 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 pantry 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 pantry. 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.
pantry 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 →