AI agents invoke run_judge to trigger actions in Root Signals MCP Server. 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 executes an evaluation/judgment operation on potentially arbitrary inputs, which constitutes code/operation execution. While the operation itself is non-destructive and read-only in its effects (it produces quality assessments without modifying data), it involves executing external logic whose behavior and outputs depend on the arguments provided.
From the tool's definition Tool performs 'run_judge' which executes a judge evaluation by ID, an operation that triggers external computation and produces variable outputs based on arguments (the judge ID and presumably evaluated content).
Documented attack patterns abuse exactly the kind of access run_judge gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Root Signals MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for run_judge:
{
"version": "1",
"default": "deny",
"tools": {
"run_judge": {
"limits": [
{
"counter": "run_judge_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_judge 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.
Free to start. No card required.
Run a judge using a Scorable judge by ID. It is categorised as a Execute tool in the Root Signals MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Root Signals MCP Server MCP server in PolicyLayer and add a rule for run_judge: 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 Root Signals MCP Server. Nothing to install.
run_judge 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 run_judge 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 run_judge. 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.
run_judge is provided by the Root Signals MCP Server MCP server (root-signals/scorable-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Root Signals MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 Root Signals MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.