AI agents use close_conversation to create or update resources in Intercom Articles MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Intercom Articles MCP Server environment.
Closing a conversation is a Write operation rather than Execute because it modifies data state reversibly without running arbitrary code or external processes. It is not Destructive because the action can be undone (conversations can be reopened).
From the tool's definition The tool name 'close_conversation' describes a state-changing action that modifies the status of a conversation object in Intercom.
Documented attack patterns abuse exactly the kind of access close_conversation gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Intercom Articles MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for close_conversation:
{
"version": "1",
"default": "deny",
"tools": {
"close_conversation": {
"limits": [
{
"counter": "close_conversation_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}close_conversation 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.
Close an Intercom conversation. It is categorised as a Write tool in the Intercom Articles MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Intercom Articles MCP Server MCP server in PolicyLayer and add a rule for close_conversation: 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 Intercom Articles MCP Server. Nothing to install.
close_conversation 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 close_conversation 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 close_conversation. 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.
close_conversation is provided by the Intercom Articles MCP Server MCP server (kaosensei/intercom-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Intercom Articles 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.
16 Intercom Articles MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.