scf_trigger_evidence_assessment · Scf MCP: Risk & Policy

WHAT IT DOES

What scf_trigger_evidence_assessment does on Scf

AI agents invoke scf_trigger_evidence_assessment 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_trigger_evidence_assessment needs a policy

This tool queues an external AI assessment operation, making it an Execute action rather than a simple Write. While labeled 'write', the core function is triggering/invoking an assessment process whose outcome and side effects depend on the input evidence and the AI agent's behavior. The async nature and polling requirement indicate orchestration of an external computational task.

From the tool's definition Tool description states 'Queue an AI assessment of a single evidence file' and explicitly labels it 'write — editor+ role'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

scf_trigger_evidence_assessment Rate-limited

scf_trigger_evidence_assessment 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_trigger_evidence_assessment": {
      "limits": [
        {
          "counter": "scf_trigger_evidence_assessment_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_trigger_evidence_assessment

What does the scf_trigger_evidence_assessment tool do? +

Queue an AI assessment of a single evidence file (write — editor+ role, async). Returns a pending record; poll scf_get_evidence_assessment until status is sufficient/partial/insufficient. 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_trigger_evidence_assessment? +

Register the Scf MCP server in PolicyLayer and add a rule for scf_trigger_evidence_assessment: 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_trigger_evidence_assessment? +

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

Can I rate-limit scf_trigger_evidence_assessment? +

Yes. Add a rate_limit block to the scf_trigger_evidence_assessment 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_trigger_evidence_assessment completely? +

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

scf_trigger_evidence_assessment 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.