score_batch · Sentinel Signal MCP: Risk & Policy

WHAT IT DOES

What score_batch does on Sentinel Signal MCP

AI agents invoke score_batch to trigger actions in Sentinel Signal MCP. 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 score_batch needs a policy

This tool executes batch scoring operations against an external healthcare claims workflow scoring service. It triggers computational processing (denial risk, prior authorization, reimbursement assessment) on up to 25 items at once.

From the tool's definition 'Score up to 25 workflow items sequentially in one request (POST /v1/score/batch)' — triggers external scoring operations via POST request

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

score_batch Rate-limited

score_batch 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": {
    "score_batch": {
      "limits": [
        {
          "counter": "score_batch_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 Sentinel Signal MCP, so you can run agents against it safely.

FAQ

Questions about score_batch

What does the score_batch tool do? +

Score up to 25 workflow items sequentially in one request (POST /v1/score/batch). It is categorised as a Execute tool in the Sentinel Signal MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on score_batch? +

Register the Sentinel Signal MCP server in PolicyLayer and add a rule for score_batch: 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 Sentinel Signal MCP. Nothing to install.

What risk level is score_batch? +

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

Can I rate-limit score_batch? +

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

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

score_batch is provided by the Sentinel Signal MCP server (sentinelsignal/sentinel-signal-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.