AI agents call search_users to retrieve information from Zendesk without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves user data without side effects. It performs a lookup query against the Zendesk user database. There is no data modification, deletion, or execution of code/commands. The blast radius of misuse is minimal—an AI could retrieve user contact information, but this is a standard read operation typical of support systems.
From the tool's definition Tool name is 'search_users' and description states 'Search for Zendesk users by name or email.' The verb 'search' and the action of querying user information by name or email are classic read operations with no modification, deletion, or execution of external…
Attacks that exploit this kind of access
Search for Zendesk users by name or email. It is categorised as a Read tool in the Zendesk MCP Server, which means it retrieves data without modifying state.
Register the Zendesk MCP server in PolicyLayer and add a rule for search_users: 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.
search_users 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 search_users 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 search_users. 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.
search_users 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 →