Check for messages sent to your agent.
AI agents call aip_check_messages to retrieve information from Aip Identity without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves incoming messages directed at the agent identity without creating, modifying, or deleting data. It is a query operation with no side effects, fitting the Read category. Severity is low because message retrieval poses minimal risk even if misused by an AI agent—it only exposes data the agent is authorized to receive.
From the tool's definition Tool description: 'Check for messages sent to your agent.' The verb 'check' and the retrieval-focused purpose indicate this tool queries or retrieves existing messages without modification.
Attacks that exploit this kind of access
Check for messages sent to your agent. It is categorised as a Read tool in the Aip Identity MCP Server, which means it retrieves data without modifying state.
Register the Aip Identity MCP server in PolicyLayer and add a rule for aip_check_messages: 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 Aip Identity. Nothing to install.
aip_check_messages 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 aip_check_messages 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 aip_check_messages. 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.
aip_check_messages is provided by the Aip Identity MCP server (the-nexus-guard/aip-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 →