Get the health status of the gateway and all connected MCP servers.
AI agents call gateway.health to retrieve information from PMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves system health and status information with no capability to modify, delete, or execute operations. It is a monitoring/diagnostic read operation with minimal risk profile. The blast radius of misuse is negligible—an AI agent could spam health checks but cannot cause data loss, financial impact, or system damage through this tool alone.
From the tool's definition Tool name 'gateway.health' and description 'Get the health status of the gateway and all connected MCP servers' indicate a read-only query operation that retrieves status information without modifying any state or triggering side effects.
Documented attack patterns abuse exactly the kind of access gateway.health gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and PMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for gateway.health:
{
"version": "1",
"default": "deny",
"tools": {
"gateway.health": {}
}
}gateway.health 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.
Get the health status of the gateway and all connected MCP servers. It is categorised as a Read tool in the PMCP MCP Server, which means it retrieves data without modifying state.
Register the P MCP server in PolicyLayer and add a rule for gateway.health: 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 PMCP. Nothing to install.
gateway.health 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 gateway.health 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 gateway.health. 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.
gateway.health is provided by the P MCP server (viperjuice/pmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from PMCP, 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.
26 PMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.