Scan project files for OWASP Top-10 security vulnerabilities using pattern matching. Detects SQL injection (CWE-89), XSS (CWE-79), command injection (CWE-78), path traversal (CWE-22), hardcoded secrets (CWE-798), insecure crypto (CWE-327), open redirects (CWE-601), and SSRF (CWE-918). Skips test ...
AI agents call scan_security to retrieve information from Trace without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes code patterns from project files to identify potential vulnerabilities, but performs no modifications, deletions, or state changes. It is a static security scanner that queries source code and returns findings—a pure read operation. The explicit 'Read-only' statement and JSON return format confirm it has no side effects beyond data retrieval and analysis.
From the tool's definition Tool description explicitly states 'Read-only' and 'pattern-based security audit' that 'Scans project files' and 'Returns JSON'.
Documented attack patterns abuse exactly the kind of access scan_security gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Trace, and nothing reaches the server without passing your rules. This is the rule we recommend for scan_security:
{
"version": "1",
"default": "deny",
"tools": {
"scan_security": {}
}
}scan_security is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Scan project files for OWASP Top-10 security vulnerabilities using pattern matching. Detects SQL injection (CWE-89), XSS (CWE-79), command injection (CWE-78), path traversal (CWE-22), hardcoded secrets (CWE-798), insecure crypto (CWE-327), open redirects (CWE-601), and SSRF (CWE-918). Skips test files. Use for pattern-based security audit. For data-flow-aware analysis use taint_analysis instead. Read-only. Returns JSON: { findings: [{ rule, severity, cwe, file, line, message }], total, summary }. It is categorised as a Read tool in the Trace MCP Server, which means it retrieves data without modifying state.
Register the Trace MCP server in PolicyLayer and add a rule for scan_security: 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 Trace. Nothing to install.
scan_security is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the scan_security 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.
Set action: deny in the PolicyLayer policy for scan_security. 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.
scan_security is provided by the Trace MCP server (nikolai-vysotskyi/trace-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 178 Trace tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
178 Trace tools catalogued and risk-classified — across an index of 42,500+ MCP servers.