AI agents call get_user 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 information without modifying, deleting, or executing any operations. It has a narrow scope (user lookup by ID) and returns basic metadata. Misuse by an AI agent would result in information disclosure only—no destructive or financial impact. The blast radius is limited to exposing user profile data already accessible to authenticated Zendesk users.
From the tool's definition Tool name is 'get_user' and description states 'Get details of a Zendesk user by ID. Returns name, email, role, organization, tags.' The verb 'Get' and action of returning user details with no modification capability indicate a read-only operation.
Attacks that exploit this kind of access
Get details of a Zendesk user by ID. Returns name, email, role, organization, tags. 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 get_user: 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.
get_user 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 get_user 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 get_user. 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.
get_user 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 →