Check for new messages
AI agents call check to retrieve information from Claude IPC MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation that retrieves or queries message data. It has no side effects and does not create, modify, delete, or execute any operations. The action of 'checking for messages' is inherently a data retrieval task. The low severity reflects minimal blast radius—an AI agent checking messages cannot cause harm through this tool alone.
From the tool's definition Tool name 'check' with description 'Check for new messages' indicates a polling or querying operation that retrieves message state without modification.
Attacks that exploit this kind of access
Check for new messages. It is categorised as a Read tool in the Claude IPC MCP MCP Server, which means it retrieves data without modifying state.
Register the Claude IPC MCP server in PolicyLayer and add a rule for check: 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 Claude IPC MCP. Nothing to install.
check 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 check 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 check. 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.
check is provided by the Claude IPC MCP server (jdez427/claude-ipc-mcp). 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 →