AI agents invoke reliability_reset to trigger actions in AgentPay. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool forcibly resets a circuit breaker state, triggering an immediate operational change in infrastructure behavior. It doesn't merely read or write data — it executes a state transition that directly affects system reliability controls. Misuse could prematurely resume calls to a still-failing backend, causing cascading failures or unexpected financial charges from tool API calls resuming at scale.
From the tool's definition Force-close a tripped circuit breaker for a tool, allowing calls to resume immediately
Attacks that exploit this kind of access
Force-close a tripped circuit breaker for a tool, allowing calls to resume immediately. Use when a backend has recovered but the circuit hasn. It is categorised as a Execute tool in the AgentPay MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the AgentPay MCP server in PolicyLayer and add a rule for reliability_reset: 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_reset is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the reliability_reset 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_reset. 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_reset 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 →