Detect the operating system, available runtimes (node, npm, uvx, python, git), and installed AI clients (Cursor, Claude Desktop, VS Code, OpenClaw, Claude Code)
AI agents call detect_system to retrieve information from Cursor MCP Installer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads and queries system state—it gathers information about the operating system, installed runtimes, and AI client presence. It has no side effects, does not modify data or configuration, and does not execute arbitrary code. It is a straightforward information-retrieval operation fitting the Read category.
From the tool's definition Tool performs detection and inspection of system properties: 'Detect the operating system, available runtimes (node, npm, uvx, python, git), and installed AI clients'. No mutations, modifications, or execution of arbitrary operations.
Documented attack patterns abuse exactly the kind of access detect_system gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cursor MCP Installer, and nothing reaches the server without passing your rules. This is the rule we recommend for detect_system:
{
"version": "1",
"default": "deny",
"tools": {
"detect_system": {}
}
}detect_system 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.
Detect the operating system, available runtimes (node, npm, uvx, python, git), and installed AI clients (Cursor, Claude Desktop, VS Code, OpenClaw, Claude Code). It is categorised as a Read tool in the Cursor MCP Installer MCP Server, which means it retrieves data without modifying state.
Register the Cursor MCP Installer MCP server in PolicyLayer and add a rule for detect_system: 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 Cursor MCP Installer. Nothing to install.
detect_system 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 detect_system 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 detect_system. 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.
detect_system is provided by the Cursor MCP Installer MCP server (matthewdcage/cursor-mcp-installer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Cursor MCP Installer, 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.
3 Cursor MCP Installer tools catalogued and risk-classified — across an index of 43,000+ MCP servers.