update_tracking
AI agents use update_tracking to create or update resources in AdminAgent — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AdminAgent environment.
The tool name suggests modifying tracking information (likely shipment/order tracking details), which is a reversible write operation. No evidence it deletes data (would be Destructive) or executes arbitrary code (would be Execute). In a Shopify Admin context, updating tracking is a standard write operation.
From the tool's definition Tool name 'update_tracking' on a Shopify Admin MCP server; sibling tools include order/fulfillment management operations indicating transactional context. Description is empty, reducing confidence.
Attacks that exploit this kind of access
update_tracking. It is categorised as a Write tool in the AdminAgent MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the AdminAgent MCP server in PolicyLayer and add a rule for update_tracking: 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 AdminAgent. Nothing to install.
update_tracking 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 update_tracking 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 update_tracking. 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.
update_tracking is provided by the AdminAgent MCP server (rushikeshmore/admin-agent). 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 →