run_eval

Run the offline eval harness against the held-out intent set. Returns aggregate scores and per-intent results.

SERVERAdia Ai SOURCE@adia-ai/mcp

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade C, identity unverified Pull the record →

This record as markdown: /tools/adia-ai-mcp/run-eval.md

WHAT IT DOES

What run_eval does on Adia Ai

AI agents invoke run_eval to trigger actions in Adia Ai. 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_eval is rated High

run_eval triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs run_eval safely

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

run_eval Rate-limited

run_eval 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_eval": {
      "limits": [
        {
          "counter": "run_eval_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 Adia Ai, apply this rule, and every run_eval call is checked against it from then on.

FAQ

Questions about run_eval

What does the run_eval tool do? +

Run the offline eval harness against the held-out intent set. Returns aggregate scores and per-intent results. It is categorised as a Execute tool in the Adia Ai 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_eval? +

Register the Adia Ai MCP server in PolicyLayer and add a rule for run_eval: 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 Adia Ai. Nothing to install.

What risk level is run_eval? +

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

Can I rate-limit run_eval? +

Yes. Add a rate_limit block to the run_eval 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_eval completely? +

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

run_eval is provided by the Adia Ai MCP server (@adia-ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Adia Ai, and thousands of servers like it.

This server

All 43 Adia Ai tools → High-risk tools on this server →

Across the catalogue

run on 0sec →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 →