This record as markdown: /tools/heznpc-airmcp/get-unread-count.md
What get_unread_count does on AirMCP
AI agents call get_unread_count to retrieve information from AirMCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why get_unread_count is rated Low
This tool queries email metadata (unread count) without modifying, deleting, or executing any operations. It is a straightforward data retrieval operation with minimal security impact. The blast radius of misuse is very low—an agent could learn how many unread messages exist, but cannot access message content, delete messages, send emails, or perform any destructive actions.
From the tool's definition Tool name is 'get_unread_count' and description states 'Get unread message count across all mailboxes.' The verb 'Get' and action of retrieving a count are read-only operations with no side effects.
Attacks that exploit this kind of access
The rule that runs get_unread_count safely
PolicyLayer is an MCP gateway: it sits between your AI agents and AirMCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_unread_count, this is the rule to start with:
get_unread_count is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect AirMCP, apply this rule, and every get_unread_count call is checked against it from then on.
Questions about get_unread_count
Get unread message count across all mailboxes. It is categorised as a Read tool in the AirMCP MCP Server, which means it retrieves data without modifying state.
Register the Air MCP server in PolicyLayer and add a rule for get_unread_count: 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 AirMCP. Nothing to install.
get_unread_count 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 get_unread_count 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 get_unread_count. 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.
get_unread_count is provided by the Air MCP server (airmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Air, and thousands of servers like it.
This server
Across the catalogue