AI agents use send_ticket_reply to create or update resources in Gorgias — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gorgias environment.
This tool writes/creates new data (outbound replies) in a reversible manner. While described as 'gated' (suggesting some access controls), sending replies modifies ticket state and customer communication history. It does not execute arbitrary code, delete data, or move money, so it is Write rather than Execute, Destructive, or Financial.
From the tool's definition Tool name 'send_ticket_reply' and server description stating it 'send[s] outbound replies (gated)' indicates the tool creates and sends customer-facing messages in support tickets.
Attacks that exploit this kind of access
send_ticket_reply. It is categorised as a Write tool in the Gorgias MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gorgias MCP server in PolicyLayer and add a rule for send_ticket_reply: 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 Gorgias. Nothing to install.
send_ticket_reply 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 send_ticket_reply 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 send_ticket_reply. 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.
send_ticket_reply is provided by the Gorgias MCP server (nobanks/gorgias-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 →