Get OWASP Top 10 for LLM Applications 2025 items with CWE mappings.
AI agents call get_llm_top10 to retrieve information from Security Framework without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries security framework reference data (OWASP Top 10 for LLM Applications and associated CWE mappings). It is a pure read operation that returns informational content from a security database. An AI agent using this tool can only access existing security guidance documentation; there is no risk of unintended data modification, deletion, execution, or financial impact.
From the tool's definition Tool description states 'Get OWASP Top 10 for LLM Applications 2025 items with CWE mappings' — a retrieval operation. The verb 'Get' indicates data fetching with no modification or execution capabilities.
Documented attack patterns abuse exactly the kind of access get_llm_top10 gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Security Framework, and nothing reaches the server without passing your rules. This is the rule we recommend for get_llm_top10:
{
"version": "1",
"default": "deny",
"tools": {
"get_llm_top10": {}
}
}get_llm_top10 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.
Get OWASP Top 10 for LLM Applications 2025 items with CWE mappings. It is categorised as a Read tool in the Security Framework MCP Server, which means it retrieves data without modifying state.
Register the Security Framework MCP server in PolicyLayer and add a rule for get_llm_top10: 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 Security Framework. Nothing to install.
get_llm_top10 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 get_llm_top10 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 get_llm_top10. 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.
get_llm_top10 is provided by the Security Framework MCP server (zer0-kr/security-framework-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Security Framework, 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.
41 Security Framework tools catalogued and risk-classified — across an index of 43,000+ MCP servers.