run_sast_scan · Sentinel MCP Server MCP: Risk & Policy

WHAT IT DOES

What run_sast_scan does on Sentinel MCP Server

AI agents invoke run_sast_scan to trigger actions in Sentinel MCP Server. 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 run_sast_scan needs a policy

This tool executes an external security scanner (Semgrep) whose behavior depends entirely on the code or files provided as arguments. While the primary intent is defensive (vulnerability detection), an AI agent could misuse it to scan malicious payloads, trigger resource exhaustion via large inputs, or abuse the scanning infrastructure.

From the tool's definition Tool description states 'Run SAST scan using Semgrep' — the verb 'Run' combined with Semgrep (a code scanning engine) indicates execution of static analysis on supplied code/files. SAST scans analyze code patterns and can trigger on arbitrary input.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_sast_scan Rate-limited

run_sast_scan 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": {
    "run_sast_scan": {
      "limits": [
        {
          "counter": "run_sast_scan_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 MCP Server, so you can run agents against it safely.

FAQ

Questions about run_sast_scan

What does the run_sast_scan tool do? +

Run SAST scan using Semgrep. It is categorised as a Execute tool in the Sentinel MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on run_sast_scan? +

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

What risk level is run_sast_scan? +

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

Can I rate-limit run_sast_scan? +

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

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

run_sast_scan is provided by the Sentinel MCP Server MCP server (pranjal-lnct/scurity-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.