scf_bulk_assess_evidence · Scf MCP: Risk & Policy

WHAT IT DOES

What scf_bulk_assess_evidence does on Scf

AI agents invoke scf_bulk_assess_evidence to trigger actions in Scf. 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 scf_bulk_assess_evidence needs a policy

This tool triggers AI assessment processes on evidence files — it doesn't merely write data, but executes an asynchronous AI evaluation pipeline. 'Queue AI assessments' indicates external computation is triggered whose effects depend on the evidence files provided. The blast radius is high because bulk AI assessments (up to 50) could affect compliance determinations, risk scores, or audit outcomes if misused.

From the tool's definition Queue AI assessments for multiple evidence files (write — editor+ role, async, max 50)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

scf_bulk_assess_evidence Rate-limited

scf_bulk_assess_evidence 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": {
    "scf_bulk_assess_evidence": {
      "limits": [
        {
          "counter": "scf_bulk_assess_evidence_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 Scf, so you can run agents against it safely.

FAQ

Questions about scf_bulk_assess_evidence

What does the scf_bulk_assess_evidence tool do? +

Queue AI assessments for multiple evidence files (write — editor+ role, async, max 50). Provide evidence_id, file_ids, and/or assess_unassessed. Returns count queued. It is categorised as a Execute tool in the Scf MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on scf_bulk_assess_evidence? +

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

What risk level is scf_bulk_assess_evidence? +

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

Can I rate-limit scf_bulk_assess_evidence? +

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

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

scf_bulk_assess_evidence is provided by the Scf MCP server (mcp-server-scf). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.