scf_trigger_vendor_research · Scf MCP: Risk & Policy

WHAT IT DOES

What scf_trigger_vendor_research does on Scf

AI agents invoke scf_trigger_vendor_research 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_vendor_research needs a policy

Although the tool's ultimate purpose is informational (gathering security intelligence), it actively executes research operations against external systems (HIBP, NVD APIs, public sources) triggered by user input. This crosses the threshold from Read (passive retrieval) to Execute (triggering external operations).

From the tool's definition Tool description states it 'Queue AI security research for a vendor' and 'Checks HIBP breach data, NVD vulnerabilities, and public posture' — this triggers external operations (security research, database queries, API calls) whose effects depend on the vendor…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

scf_trigger_vendor_research Rate-limited

scf_trigger_vendor_research 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_vendor_research": {
      "limits": [
        {
          "counter": "scf_trigger_vendor_research_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_vendor_research

What does the scf_trigger_vendor_research tool do? +

Queue AI security research for a vendor (write — editor+ role, async). Checks HIBP breach data, NVD vulnerabilities, and public posture. Returns a task ID; poll scf_get_vendor_research. 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_vendor_research? +

Register the Scf MCP server in PolicyLayer and add a rule for scf_trigger_vendor_research: 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_vendor_research? +

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

Can I rate-limit scf_trigger_vendor_research? +

Yes. Add a rate_limit block to the scf_trigger_vendor_research 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_vendor_research completely? +

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

scf_trigger_vendor_research 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.