Scan all MCP servers for security vulnerabilities. Connects to each server, retrieves tool definitions, and runs pattern-based detection for prompt injection, tool poisoning, credential exposure, and other threats. Returns findings with severity levels and baseline comparison.
AI agents call audit_security to retrieve information from Claude Code Organizer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads/scans MCP server configurations and tool definitions for security issues — it retrieves data without modifying or deleting anything. However, it connects to external servers and retrieves their tool definitions, which could expose sensitive information about infrastructure.
From the tool's definition Scan all MCP servers for security vulnerabilities. Connects to each server, retrieves tool definitions, and runs pattern-based detection
Documented attack patterns abuse exactly the kind of access audit_security gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Claude Code Organizer, and nothing reaches the server without passing your rules. This is the rule we recommend for audit_security:
{
"version": "1",
"default": "deny",
"tools": {
"audit_security": {}
}
}audit_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 all MCP servers for security vulnerabilities. Connects to each server, retrieves tool definitions, and runs pattern-based detection for prompt injection, tool poisoning, credential exposure, and other threats. Returns findings with severity levels and baseline comparison. It is categorised as a Read tool in the Claude Code Organizer MCP Server, which means it retrieves data without modifying state.
Register the Claude Code Organizer MCP server in PolicyLayer and add a rule for audit_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 Claude Code Organizer. Nothing to install.
audit_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 audit_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 audit_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.
audit_security is provided by the Claude Code Organizer MCP server (mcpware/cross-code-organizer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Code Organizer, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 Claude Code Organizer tools catalogued and risk-classified — across an index of 43,000+ MCP servers.