Manually check for new messages from other Claude Code instances. Messages are normally pushed automatically via channel notifications, but you can use this as a fallback.
AI agents call check_messages to retrieve information from Claude Peers without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool purely retrieves message data from a local broker daemon without side effects. It is a read operation analogous to checking an inbox. No data is created, modified, deleted, or executed. Low severity because it only exposes messages already transmitted between trusted local agents in the same environment, with no blast radius beyond information disclosure of inter-agent communications.
From the tool's definition Tool description states 'Manually check for new messages from other Claude Code instances' and 'Messages are normally pushed automatically via channel notifications, but you can use this as a fallback.' The operation retrieves/queries messages with no stated…
Documented attack patterns abuse exactly the kind of access check_messages gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Peers, and nothing reaches the server without passing your rules. This is the rule we recommend for check_messages:
{
"version": "1",
"default": "deny",
"tools": {
"check_messages": {}
}
}check_messages is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Manually check for new messages from other Claude Code instances. Messages are normally pushed automatically via channel notifications, but you can use this as a fallback. It is categorised as a Read tool in the Claude Peers MCP Server, which means it retrieves data without modifying state.
Register the Claude Peers MCP server in PolicyLayer and add a rule for 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 Claude Peers. Nothing to install.
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 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 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.
check_messages is provided by the Claude Peers MCP server (louislva/claude-peers-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Peers, 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.
4 Claude Peers tools catalogued and risk-classified — across an index of 43,000+ MCP servers.