AI agents use customize_order to create or update resources in Mcp Otle — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Otle environment.
This tool modifies an order with special requests, which is a Write operation (creating/updating order data). Severity is medium because it affects an order in a simulated context, though 'Results may vary' suggests unpredictable outcomes. Confidence is moderate because the description is vague and doesn't detail exactly what data is written or how reversible the changes are.
From the tool's definition 'Make special requests for your order' — modifies an existing order by adding special instructions or customizations
Attacks that exploit this kind of access
Make special requests for your order. Results may vary. It is categorised as a Write tool in the Mcp Otle MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Otle MCP server in PolicyLayer and add a rule for customize_order: 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 Mcp Otle. Nothing to install.
customize_order 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 customize_order 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 customize_order. 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.
customize_order is provided by the Mcp Otle MCP server (yoshisaurus/mcp-otle). 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 →