reliability_config · AgentPay MCP: Risk & Policy

WHAT IT DOES

What reliability_config does on AgentPay

AI agents use reliability_config to create or update resources in AgentPay — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your AgentPay environment.

WHY IT NEEDS A POLICY

Why reliability_config needs a policy

This tool creates or modifies reliability configuration data (failure threshold, recovery timeout, request timeout) for specific tools. While reversible (settings can be updated again), the changes take effect immediately and could disrupt payment processing or autonomous agent behavior if misconfigured. Categorized as Write rather than Execute because it updates configuration state, not triggers external operations.

From the tool's definition Tool description states 'Update reliability settings' — a modification operation. The name 'reliability_config' and context within an AgentPay payment gateway server indicate this modifies configuration parameters for tool behavior.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

reliability_config Rate-limited

reliability_config stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "reliability_config": {
      "limits": [
        {
          "counter": "reliability_config_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches AgentPay, so you can run agents against it safely.

FAQ

Questions about reliability_config

What does the reliability_config tool do? +

Update reliability settings for a specific tool — failure threshold, recovery timeout, and request timeout. Changes take effect immediately. It is categorised as a Write tool in the AgentPay MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on reliability_config? +

Register the AgentPay MCP server in PolicyLayer and add a rule for reliability_config: 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.

What risk level is reliability_config? +

reliability_config is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit reliability_config? +

Yes. Add a rate_limit block to the reliability_config 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.

How do I block reliability_config completely? +

Set action: deny in the PolicyLayer policy for reliability_config. 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.

What MCP server provides reliability_config? +

reliability_config 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.