run_judge_loop

Execute a full judge-fix-verify loop: calls a tool, judges the output, and if it fails,

SERVERNodebench SOURCEnodebench-mcp

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-homenshum-nodebench/run-judge-loop.md

WHAT IT DOES

What run_judge_loop does on Nodebench

AI agents invoke run_judge_loop to trigger actions in Nodebench. 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.

RISK

Why run_judge_loop is rated High

The tool executes arbitrary tool calls in a loop with conditional logic, which represents autonomous code/operation execution whose effects depend on which tools are invoked and arguments passed. This is Execute rather than Write because it can trigger any tool and repeat operations, and the looping behavior with failure handling means effects are not easily predictable or reversible.

From the tool's definition Tool name contains 'run' and description states 'Execute a full judge-fix-verify loop: calls a tool, judges the output, and if it fails,' indicating execution of external operations with conditional branching based on outcomes.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs run_judge_loop safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For run_judge_loop, this is the rule to start with:

run_judge_loop Rate-limited

run_judge_loop stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run_judge_loop": {
      "limits": [
        {
          "counter": "run_judge_loop_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every run_judge_loop call is checked against it from then on.

FAQ

Questions about run_judge_loop

What does the run_judge_loop tool do? +

Execute a full judge-fix-verify loop: calls a tool, judges the output, and if it fails,. It is categorised as a Execute tool in the Nodebench MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_judge_loop? +

Register the Nodebench MCP server in PolicyLayer and add a rule for run_judge_loop: 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 Nodebench. Nothing to install.

What risk level is run_judge_loop? +

run_judge_loop is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit run_judge_loop? +

Yes. Add a rate_limit block to the run_judge_loop 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 run_judge_loop completely? +

Set action: deny in the PolicyLayer policy for run_judge_loop. 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 run_judge_loop? +

run_judge_loop is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Nodebench, and thousands of servers like it.

This server

All 824 Nodebench tools → High-risk tools on this server →

Across the catalogue

shortcuts_run on Apple Apps MCP →run_emba_scan on EMBA-MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →