run_verifier · Scrumdo MCP: Risk & Policy

WHAT IT DOES

What run_verifier does on Scrumdo

AI agents invoke run_verifier to trigger actions in Scrumdo. 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 run_verifier needs a policy

The tool performs an action ('run') that executes some verification process, which is characteristic of Execute category tools that trigger operations whose effects depend on context. Without a description, confidence is lowered but the name strongly indicates code/logic execution.

From the tool's definition Tool name 'run_verifier' combined with context of ScrumDo board operations suggests execution of verification logic or tests. The empty description prevents precise determination, but the verb 'run' indicates triggering an external operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_verifier Rate-limited

run_verifier 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_verifier": {
      "limits": [
        {
          "counter": "run_verifier_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 Scrumdo, so you can run agents against it safely.

FAQ

Questions about run_verifier

What does the run_verifier tool do? +

run_verifier. It is categorised as a Execute tool in the Scrumdo 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_verifier? +

Register the Scrumdo MCP server in PolicyLayer and add a rule for run_verifier: 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 Scrumdo. Nothing to install.

What risk level is run_verifier? +

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

Can I rate-limit run_verifier? +

Yes. Add a rate_limit block to the run_verifier 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_verifier completely? +

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

run_verifier is provided by the Scrumdo MCP server (scrumdollc/scrumdo-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.