Check the ONS service status and get counts.
AI agents call ons_health to retrieve information from Open Neural Substrate 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 check of service health and retrieves status metrics. It has no side effects, does not execute code or commands, does not modify data, and does not delete anything. The blast radius of misuse is minimal—an agent could at most spam health checks or learn that a service is down, neither of which causes harm.
From the tool's definition Tool name 'ons_health' and description 'Check the ONS service status and get counts' indicate a query/monitoring operation that retrieves status information without modifying, executing operations, or deleting data.
Attacks that exploit this kind of access
Check the ONS service status and get counts. It is categorised as a Read tool in the Open Neural Substrate MCP Server, which means it retrieves data without modifying state.
Register the Open Neural Substrate MCP server in PolicyLayer and add a rule for ons_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 Open Neural Substrate. Nothing to install.
ons_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 ons_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 ons_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.
ons_health is provided by the Open Neural Substrate MCP server (pedroknigge/open-neural-substrate). 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 →