Escanea el código fuente del proyecto buscando patrones de código vulnerable como XSS, eval(), innerHTML sin sanitizar, tokens en localStorage, etc. Retorna vulnerabilidades con ubicación exacta y soluciones.
AI agents call scan_code_vulnerabilities to retrieve information from MCP Security Scanner without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs static code analysis by examining source code for security vulnerabilities (XSS, eval, innerHTML, tokens in localStorage). It is a read-only operation that queries and retrieves vulnerability information without modifying the codebase or executing external operations.
From the tool's definition Tool description states it 'Escanea' (scans) the code searching for vulnerable patterns and 'Retorna vulnerabilidades' (returns vulnerabilities) with exact location and solutions.
Attacks that exploit this kind of access
Escanea el código fuente del proyecto buscando patrones de código vulnerable como XSS, eval(), innerHTML sin sanitizar, tokens en localStorage, etc. Retorna vulnerabilidades con ubicación exacta y soluciones. It is categorised as a Read tool in the MCP Security Scanner MCP Server, which means it retrieves data without modifying state.
Register the MCP Security Scanner MCP server in PolicyLayer and add a rule for scan_code_vulnerabilities: 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 Security Scanner. Nothing to install.
scan_code_vulnerabilities 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_code_vulnerabilities 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_code_vulnerabilities. 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_code_vulnerabilities is provided by the MCP Security Scanner MCP server (jmitac/mcp-security-scanner). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →