AI agents call detect_package_manager to retrieve information from VibeServe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs detection/analysis of the development environment to determine the active package manager. It retrieves or queries configuration state to identify whether npm, yarn, or pnpm is in use. This is a read-only operation with no side effects—it does not execute package manager commands, create/modify files, or trigger external operations.
From the tool's definition Tool name 'detect_package_manager' and description 'Detect which package manager to use (npm, yarn, pnpm)' indicate inspection/detection of environment state without modification or execution of commands.
Attacks that exploit this kind of access
Detect which package manager to use (npm, yarn, pnpm). It is categorised as a Read tool in the VibeServe MCP Server, which means it retrieves data without modifying state.
Register the VibeServe MCP server in PolicyLayer and add a rule for detect_package_manager: 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 VibeServe. Nothing to install.
detect_package_manager 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_package_manager 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_package_manager. 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_package_manager is provided by the VibeServe MCP server (ncsound919/vibeserve). 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 →