scan_agentforce · Squirex Dev MCP: Risk & Policy

WHAT IT DOES

What scan_agentforce does on Squirex Dev

AI agents invoke scan_agentforce to trigger actions in Squirex Dev. 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 scan_agentforce needs a policy

This tool executes a SAST scanning process against the current project, triggering external analysis operations. It is not merely reading static data but actively running code/analysis pipelines across the project. Misuse or misconfiguration could expose sensitive metadata or cause unintended disclosure of security findings.

From the tool's definition 'Run the full Agentforce Capability Scan (26 SAST rules across 9 categories) against the current project' — actively executes a scan operation against project files

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

scan_agentforce Rate-limited

scan_agentforce 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": {
    "scan_agentforce": {
      "limits": [
        {
          "counter": "scan_agentforce_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 Squirex Dev, so you can run agents against it safely.

FAQ

Questions about scan_agentforce

What does the scan_agentforce tool do? +

Run the full Agentforce Capability Scan (26 SAST rules across 9 categories) against the current project. Returns SARIF-structured violations covering action configuration, agent script safety, grounding security, structural dependencies, flow/prompt template security, supply chain, agentic architecture, instruction integrity, and operational reliability. It is categorised as a Execute tool in the Squirex Dev MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on scan_agentforce? +

Register the Squirex Dev MCP server in PolicyLayer and add a rule for scan_agentforce: 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 Squirex Dev. Nothing to install.

What risk level is scan_agentforce? +

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

Can I rate-limit scan_agentforce? +

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

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

scan_agentforce is provided by the Squirex Dev MCP server (squirex-dev/squirex-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.