test_evaluator · Respan MCP Server MCP: Risk & Policy

WHAT IT DOES

What test_evaluator does on Respan MCP Server

AI agents invoke test_evaluator to trigger actions in Respan 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.

WHY IT NEEDS A POLICY

Why test_evaluator needs a policy

The tool executes a trial run of an evaluator grader, which involves running code or logic against sample inputs. This is an Execute-category action since it triggers an external operation (grading execution) whose effects depend on the arguments provided. It is not merely reading data, nor does it irreversibly modify or delete anything, making Execute the most appropriate category.

From the tool's definition "Test-run a grader with sample inputs" — the tool actively runs/executes an evaluator grader against inputs, triggering external evaluation operations before a commit.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

test_evaluator Rate-limited

test_evaluator 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": {
    "test_evaluator": {
      "limits": [
        {
          "counter": "test_evaluator_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 Respan MCP Server, so you can run agents against it safely.

FAQ

Questions about test_evaluator

What does the test_evaluator tool do? +

Test-run a grader with sample inputs to verify it scores correctly BEFORE committing. Required keys in inputs: at least. It is categorised as a Execute tool in the Respan MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on test_evaluator? +

Register the Respan MCP Server MCP server in PolicyLayer and add a rule for test_evaluator: 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 Respan MCP Server. Nothing to install.

What risk level is test_evaluator? +

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

Can I rate-limit test_evaluator? +

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

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

test_evaluator is provided by the Respan MCP Server MCP server (respanai/respan-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.