AI agents call inbox-count-all to retrieve information from Moxis without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves aggregated inbox statistics across multiple instances. It performs no writes, deletions, code execution, or financial operations. The operation is purely informational with no side effects. Severity is low because inbox counts are typically non-sensitive metadata and misuse poses minimal risk.
From the tool's definition Tool name 'inbox-count-all' and description 'returns the number of items in your inboxes for all registered instances' indicate a query operation that retrieves count data without modifying or executing anything.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
returns the number of items in your inboxes for all registered instances. It is categorised as a Read tool in the Moxis MCP Server, which means it retrieves data without modifying state.
Register the Moxis MCP server in PolicyLayer and add a rule for inbox-count-all: 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 Moxis. Nothing to install.
inbox-count-all 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 inbox-count-all 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 inbox-count-all. 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.
inbox-count-all is provided by the Moxis MCP server (@xitrust-pub/moxis-mcp-server). 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 →