eval_run · Lore Context MCP: Risk & Policy

WHAT IT DOES

What eval_run does on Lore Context

AI agents invoke eval_run to trigger actions in Lore Context. 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.

WHY IT NEEDS A POLICY

Why eval_run needs a policy

This tool executes an evaluation workflow against uploaded sessions or recipe datasets. While the primary output is likely evaluation metrics (read-like), the act of 'running' an evaluation process constitutes execution of code or logic whose behavior and effects depend on arguments (the dataset, session, or recipe version supplied). It is not a simple read/query operation.

From the tool's definition 'Run retrieval evaluation over uploaded sessions or a v12/v13 recipe dataset' — the verb 'Run' combined with 'evaluation' over external datasets indicates active execution of an evaluation process whose side effects depend on the input dataset and evaluation…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

eval_run Rate-limited

eval_run 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": {
    "eval_run": {
      "limits": [
        {
          "counter": "eval_run_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Lore Context, so you can run agents against it safely.

FAQ

Questions about eval_run

What does the eval_run tool do? +

Run retrieval evaluation over uploaded sessions or a v12/v13 recipe dataset. It is categorised as a Execute tool in the Lore Context MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on eval_run? +

Register the Lore Context MCP server in PolicyLayer and add a rule for eval_run: 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 Lore Context. Nothing to install.

What risk level is eval_run? +

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

Can I rate-limit eval_run? +

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

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

eval_run is provided by the Lore Context MCP server (Lore-Context/lore-context). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.