Scan the knowledge graph for OWASP vulnerabilities: SQL injection, XSS, SSRF, path traversal, command injection
AI agents call vulnerability_scan to retrieve information from code-intel MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs static analysis or graph queries to identify potential security issues. It retrieves and reports information about vulnerabilities without creating, modifying, deleting, executing code, moving money, or triggering external operations. The 'scan' operation is a read-only inspection of existing data (the knowledge graph).
From the tool's definition Tool name is 'vulnerability_scan' and description states it 'Scan[s] the knowledge graph for OWASP vulnerabilities' — it queries/analyzes a knowledge graph to detect and report vulnerabilities, producing no side effects on the system or code being scanned.
Attacks that exploit this kind of access
Scan the knowledge graph for OWASP vulnerabilities: SQL injection, XSS, SSRF, path traversal, command injection. It is categorised as a Read tool in the code-intel MCP Server MCP Server, which means it retrieves data without modifying state.
Register the code-intel MCP Server MCP server in PolicyLayer and add a rule for vulnerability_scan: 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 code-intel MCP Server. Nothing to install.
vulnerability_scan 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 vulnerability_scan 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 vulnerability_scan. 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.
vulnerability_scan is provided by the code-intel MCP Server MCP server (vohongtho/code-intel-platform). 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 →