Decide whether to run another refinement iteration or finalize the response. Uses three stopping criteria: 1. Budget: stop if iteration >= max_iterations 2. Threshold: stop if ALL claims exceed confidence_threshold 3. Convergence: stop if average confidence didn
AI agents call arsr_should_continue to retrieve information from Mcp Arsr without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool evaluates stopping conditions (iteration count, confidence threshold, convergence) and returns a decision. It reads/checks state but does not modify data, execute code, or cause side effects. It is a pure decision/query operation within the refinement loop.
From the tool's definition Decide whether to run another refinement iteration or finalize the response. Uses three stopping criteria: Budget, Threshold, Convergence
Attacks that exploit this kind of access
Decide whether to run another refinement iteration or finalize the response. Uses three stopping criteria: 1. Budget: stop if iteration >= max_iterations 2. Threshold: stop if ALL claims exceed confidence_threshold 3. Convergence: stop if average confidence didn. It is categorised as a Read tool in the Mcp Arsr MCP Server, which means it retrieves data without modifying state.
Register the Mcp Arsr MCP server in PolicyLayer and add a rule for arsr_should_continue: 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 Mcp Arsr. Nothing to install.
arsr_should_continue 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 arsr_should_continue 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 arsr_should_continue. 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.
arsr_should_continue is provided by the Mcp Arsr MCP server (jayarrowz/mcp-arsr). 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 →