scan_directory · Semgrep MCP Server MCP: Risk & Policy

WHAT IT DOES

What scan_directory does on Semgrep MCP Server

AI agents invoke scan_directory to trigger actions in Semgrep 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 scan_directory needs a policy

This tool runs a Semgrep scan against a directory, which involves executing an external process/program on the filesystem. While primarily a read/analysis operation, it triggers external code execution (the Semgrep scanner) whose effects depend on arguments (which directory, which rules).

From the tool's definition "Führt einen Semgrep-Scan in einem Verzeichnis aus" (Executes a Semgrep scan in a directory)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

scan_directory Rate-limited

scan_directory 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_directory": {
      "limits": [
        {
          "counter": "scan_directory_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 Semgrep MCP Server, so you can run agents against it safely.

FAQ

Questions about scan_directory

What does the scan_directory tool do? +

Führt einen Semgrep-Scan in einem Verzeichnis aus. It is categorised as a Execute tool in the Semgrep 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 scan_directory? +

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

What risk level is scan_directory? +

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

Can I rate-limit scan_directory? +

Yes. Add a rate_limit block to the scan_directory 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_directory completely? +

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

scan_directory is provided by the Semgrep MCP Server MCP server (stefanskiasan/semgrep-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.