scan_repo · Trust Security MCP: Risk & Policy

WHAT IT DOES

What scan_repo does on Trust Security

AI agents invoke scan_repo to trigger actions in Trust Security. 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_repo needs a policy

The tool name 'scan_repo' strongly implies it initiates an active security scan of a repository. Based on the server description and sibling tools, this triggers external automated scanning operations (SAST). This is an Execute-category action as it runs automated analysis processes against external targets. The description is empty, which lowers confidence slightly, but the pattern is clear from context.

From the tool's definition Tool name 'scan_repo' on a server described as performing 'automated DAST and SAST scanning' of GitHub repositories. Sibling tools include 'scan_repo_and_wait', 'analyze_code_security', 'check_secrets'.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

scan_repo Rate-limited

scan_repo 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_repo": {
      "limits": [
        {
          "counter": "scan_repo_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 Trust Security, so you can run agents against it safely.

FAQ

Questions about scan_repo

What does the scan_repo tool do? +

scan_repo. It is categorised as a Execute tool in the Trust Security 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_repo? +

Register the Trust Security MCP server in PolicyLayer and add a rule for scan_repo: 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 Trust Security. Nothing to install.

What risk level is scan_repo? +

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

Can I rate-limit scan_repo? +

Yes. Add a rate_limit block to the scan_repo 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_repo completely? +

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

scan_repo is provided by the Trust Security MCP server (jaden-jjh/trust-security-scanner). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.