AI agents use clevertap_disassociate_phone to create or update resources in Clevertap — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Clevertap environment.
This tool modifies a user profile by removing the association between a phone number and the profile. It's a Write operation (reversible modification — the phone number could presumably be re-associated), but with high severity since it alters identity/authentication data for a user profile, potentially disrupting communications, authentication, or marketing targeting at scale if misused.
From the tool's definition Disassociate a phone number from its user profile in CleverTap
Attacks that exploit this kind of access
Disassociate a phone number from its user profile in CleverTap. Only works when the phone number is used as the user. It is categorised as a Write tool in the Clevertap MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Clevertap MCP server in PolicyLayer and add a rule for clevertap_disassociate_phone: 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_disassociate_phone 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 clevertap_disassociate_phone 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_disassociate_phone. 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_disassociate_phone 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 →