List the custom agent roles defined on this account (Enterprise). Read-only.
AI agents call zda_list_agent_roles to retrieve information from Zendesk Admin MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and enumerates role definitions from the Zendesk account. It performs no modifications, deletions, or external triggers. While the parent server supports destructive operations via full CRUD, this specific tool is narrowly scoped to data retrieval.
From the tool's definition Tool name contains 'list', description explicitly states 'Read-only', and the operation is to list/query custom agent roles without any side effects.
Attacks that exploit this kind of access
List the custom agent roles defined on this account (Enterprise). Read-only. It is categorised as a Read tool in the Zendesk Admin MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Zendesk Admin MCP Server MCP server in PolicyLayer and add a rule for zda_list_agent_roles: 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 Admin MCP Server. Nothing to install.
zda_list_agent_roles is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the zda_list_agent_roles 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 zda_list_agent_roles. 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.
zda_list_agent_roles is provided by the Zendesk Admin MCP Server MCP server (sniebauer/zendesk-admin-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 →