Get OWASP Top 10 for MCP Servers 2025 — security risks specific to MCP deployments.
AI agents call get_mcp_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 queries or retrieves static security reference data (OWASP Top 10 listing) from the integrated security framework. It has no side effects, does not execute code or commands, does not modify data, and does not incur financial obligations. Even if an AI agent misuses it by requesting all data, the blast radius is minimal—it simply returns informational security guidance.
From the tool's definition Tool name 'get_mcp_top10' and description 'Get OWASP Top 10 for MCP Servers 2025' indicate retrieval of published security framework data with no modification, execution, or destructive capability.
Documented attack patterns abuse exactly the kind of access get_mcp_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_mcp_top10:
{
"version": "1",
"default": "deny",
"tools": {
"get_mcp_top10": {}
}
}get_mcp_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 MCP Servers 2025 — security risks specific to MCP deployments. 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_mcp_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_mcp_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_mcp_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_mcp_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_mcp_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.