AI agents call reliability_dashboard to retrieve information from AgentPay without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and displays observability/monitoring information about system health and backend status. It requires elevated permissions (admin key) but performs only data retrieval with no side effects. The blast radius of misuse is low — an agent viewing dashboards cannot modify systems or commit financial resources. Categorized as Read rather than Other due to its straightforward retrieval nature.
From the tool's definition Tool description states 'View the full reliability dashboard' — a read-only operation that retrieves monitoring data (circuit breaker states, health metrics, recent events). No modification, deletion, or external action is performed.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
View the full reliability dashboard — circuit breaker states, health metrics (latency p50/p95/p99, success rates), and recent events for all tool backends. Requires admin key. It is categorised as a Read tool in the AgentPay MCP Server, which means it retrieves data without modifying state.
Register the AgentPay MCP server in PolicyLayer and add a rule for reliability_dashboard: 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 AgentPay. Nothing to install.
reliability_dashboard 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 reliability_dashboard 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 reliability_dashboard. 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.
reliability_dashboard is provided by the AgentPay MCP server (joepangallo/mcp-server-agentpay). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
reliability_dashboard is one line of AgentPay's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →