scan_project · MCP Shamash MCP: Risk & Policy

WHAT IT DOES

What scan_project does on MCP Shamash

AI agents invoke scan_project to trigger actions in MCP Shamash. 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_project needs a policy

This tool executes multiple security scanning tools (Semgrep for SAST, Trivy for vulnerability scanning, Gitleaks for secret detection) on a project directory. It initiates external processes and operations whose effects depend on the target and configuration.

From the tool's definition 'Performs comprehensive security scan on project directory' — triggers external security tools (Semgrep, Trivy, Gitleaks, OWASP ZAP) against a target directory

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

scan_project Rate-limited

scan_project 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_project": {
      "limits": [
        {
          "counter": "scan_project_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 MCP Shamash, so you can run agents against it safely.

FAQ

Questions about scan_project

What does the scan_project tool do? +

Performs comprehensive security scan on project directory. It is categorised as a Execute tool in the MCP Shamash 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_project? +

Register the MCP Shamash MCP server in PolicyLayer and add a rule for scan_project: 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 MCP Shamash. Nothing to install.

What risk level is scan_project? +

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

Can I rate-limit scan_project? +

Yes. Add a rate_limit block to the scan_project 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_project completely? +

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

scan_project is provided by the MCP Shamash MCP server (neotecdigital/mcp_shamash). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.