AI agents use reduce_pantry_amount to create or update resources in Pantrist — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pantrist environment.
This tool modifies an existing pantry item's stock level by applying a delta value. It mutates state (Write category) but is reversible — the amount can be changed back. It does not delete data, execute code, or involve financial transactions. Severity is medium because misuse could corrupt pantry inventory tracking across all devices in real time.
From the tool's definition Change the stock of an existing pantry item by a delta. Mutates state and returns the updated
Attacks that exploit this kind of access
Change the stock of an existing pantry item by a delta. Mutates state and returns the updated. It is categorised as a Write tool in the Pantrist MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pantrist MCP server in PolicyLayer and add a rule for reduce_pantry_amount: 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 Pantrist. Nothing to install.
reduce_pantry_amount 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 reduce_pantry_amount 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 reduce_pantry_amount. 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.
reduce_pantry_amount is provided by the Pantrist MCP server (pantrist-dev/pantrist-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 →