AI agents use import_message to create or update resources in Frontapp MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Frontapp MCP Server environment.
The tool adds new message data to an inbox, which is a reversible create/write operation. It does not execute arbitrary code, delete data, or move money. The severity is medium because importing messages could affect communication records and audit trails, and an agent misusing this could inject spam, misleading, or fraudulent messages into customer inboxes, but the action remains reversible (messages can be…
From the tool's definition Tool name 'import_message' and description 'Import a historical message to an inbox' indicate creation of new message records in Frontapp. This is a write operation that creates data in the system.
Documented attack patterns abuse exactly the kind of access import_message 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 import_message:
{
"version": "1",
"default": "deny",
"tools": {
"import_message": {
"limits": [
{
"counter": "import_message_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}import_message stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Import a historical message to an inbox. It is categorised as a Write tool in the Frontapp MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Frontapp MCP Server MCP server in PolicyLayer and add a rule for import_message: 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.
import_message 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 import_message 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 import_message. 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.
import_message 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.