analyze_code_security
AI agents call analyze_code_security to retrieve information from Trust Security without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears designed to analyze and report on code security issues rather than modify, execute, or delete. The server's stated purpose is 'Detect live website vulnerabilities...identify exposed secrets...receive structured fix plans'—all Read operations.
From the tool's definition Tool name 'analyze_code_security' suggests inspection/analysis without modification. Empty description limits confidence. Consistent with sibling tools (check_secrets, get_fix_plan, get_scan_result) which are scanning/reading operations.
Attacks that exploit this kind of access
analyze_code_security. It is categorised as a Read tool in the Trust Security MCP Server, which means it retrieves data without modifying state.
Register the Trust Security MCP server in PolicyLayer and add a rule for analyze_code_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 Trust Security. Nothing to install.
analyze_code_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 analyze_code_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 analyze_code_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.
analyze_code_security 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.
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 →