AI agents call merge_contacts to permanently remove resources in Frontapp MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Merging contacts is an irreversible operation — once two contact records are combined, the original separate identities are lost and cannot be easily restored. This is a destructive action with significant blast radius if misused by an AI agent, as customer data integrity could be permanently compromised.
From the tool's definition Merge two contacts into one
Documented attack patterns abuse exactly the kind of access merge_contacts gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Frontapp MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for merge_contacts:
{
"version": "1",
"default": "deny",
"hide": [
"merge_contacts"
]
}merge_contacts disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Merge two contacts into one. It is categorised as a Destructive tool in the Frontapp MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Frontapp MCP Server MCP server in PolicyLayer and add a rule for merge_contacts: 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 Frontapp MCP Server. Nothing to install.
merge_contacts is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the merge_contacts 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 merge_contacts. 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.
merge_contacts is provided by the Frontapp MCP Server MCP server (zqushair/frontapp-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Frontapp MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
151 Frontapp MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.