Run a standard evaluation using a Scorable evaluator by ID
AI agents invoke run_evaluation 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 triggers execution of an evaluation workflow on AI responses. While the evaluation itself is not destructive or financial, it executes external evaluation logic whose effects and outcomes depend on the input arguments (the evaluator ID, the response being evaluated, and evaluation criteria). The tool does not merely read static data—it performs a computational operation.
From the tool's definition Tool name 'run_evaluation' combined with description 'Run a standard evaluation using a Scorable evaluator by ID' indicates the tool executes an evaluation process.
Documented attack patterns abuse exactly the kind of access run_evaluation 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_evaluation:
{
"version": "1",
"default": "deny",
"tools": {
"run_evaluation": {
"limits": [
{
"counter": "run_evaluation_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}run_evaluation 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 standard evaluation using a Scorable evaluator 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_evaluation: 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_evaluation 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_evaluation 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_evaluation. 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_evaluation 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.