AI agents use solve_ticket to create or update resources in Zendesk — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zendesk environment.
Solving a ticket changes its status to 'solved', which is a state modification in Zendesk. This is a reversible write operation (tickets can be reopened), not a destructive action. Misuse could prematurely close legitimate support tickets, hence medium severity.
From the tool's definition Solve a single Zendesk ticket by ID
Attacks that exploit this kind of access
Solve a single Zendesk ticket by ID. It is categorised as a Write tool in the Zendesk MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zendesk MCP server in PolicyLayer and add a rule for solve_ticket: 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 Zendesk. Nothing to install.
solve_ticket 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 solve_ticket 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 solve_ticket. 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.
solve_ticket is provided by the Zendesk MCP server (kalchevs/zendesk-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 →