AI agents call reliability_tool_detail 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.
The tool queries and returns observability data about tool reliability and configuration state. It has no side effects, does not execute operations, does not create or modify data, and does not involve financial transactions. This is a pure read operation on monitoring/diagnostic data.
From the tool's definition Tool description states it retrieves 'detailed reliability info' including 'circuit breaker state, config, health metrics, and recent events' — these are informational queries with no modification or execution of operations.
Attacks that exploit this kind of access
Get detailed reliability info for a specific tool — circuit breaker state, config (thresholds, timeouts), health metrics, and recent events. 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_tool_detail: 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_tool_detail 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_tool_detail 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_tool_detail. 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_tool_detail 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.
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 →