AI agents call clevertap_get_events to retrieve information from Clevertap without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/queries event data and returns pagination tokens for fetching results. It performs no modifications, deletions, executions, or financial operations. The use of 'Query' and 'Returns' language confirms data retrieval only.
From the tool's definition Tool name 'clevertap_get_events' and description 'Query event data for a specific event within a date range. Returns a cursor token for paginated results' indicates a read-only retrieval operation with no side effects.
Attacks that exploit this kind of access
Query event data for a specific event within a date range. Returns a cursor token for paginated results — use clevertap_get_events_cursor to fetch subsequent pages. It is categorised as a Read tool in the Clevertap MCP Server, which means it retrieves data without modifying state.
Register the Clevertap MCP server in PolicyLayer and add a rule for clevertap_get_events: 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 Clevertap. Nothing to install.
clevertap_get_events 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 clevertap_get_events 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 clevertap_get_events. 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.
clevertap_get_events is provided by the Clevertap MCP server (ralphcorleone/clevertap-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 →