tokrepo_eval_agent · TokRepo — AI Asset Registry MCP

WHAT IT DOES

What tokrepo_eval_agent does on TokRepo — AI Asset Registry

AI agents invoke tokrepo_eval_agent to trigger actions in TokRepo — AI Asset Registry. 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 tokrepo_eval_agent needs a policy

This tool executes evaluation and verification operations against external systems (install plans, manifests, Codex installs) and can perform rollback actions that modify local state. While the description emphasizes verification and testing, the ability to 'run' operations and trigger rollbacks places it in Execute rather than Read.

From the tool's definition Tool description states it will 'Run TokRepo agent-native evals through the CLI' and explicitly mentions 'rollback' operations. The phrase 'Run...through the CLI' indicates execution of external operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

tokrepo_eval_agent Rate-limited

tokrepo_eval_agent 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": {
    "tokrepo_eval_agent": {
      "limits": [
        {
          "counter": "tokrepo_eval_agent_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 TokRepo — AI Asset Registry, so you can run agents against it safely.

FAQ

Questions about tokrepo_eval_agent

What does the tokrepo_eval_agent tool do? +

Run TokRepo agent-native evals through the CLI. Verifies filtered search, install-plan contracts, metadata quality reporting, Codex install verification, manifest state, and rollback using temporary local state. It is categorised as a Execute tool in the TokRepo — AI Asset Registry MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on tokrepo_eval_agent? +

Register the TokRepo — AI Asset Registry MCP server in PolicyLayer and add a rule for tokrepo_eval_agent: 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 TokRepo — AI Asset Registry. Nothing to install.

What risk level is tokrepo_eval_agent? +

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

Can I rate-limit tokrepo_eval_agent? +

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

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

tokrepo_eval_agent is provided by the TokRepo — AI Asset Registry MCP server (tokrepo-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.