macos_login_items
AI agents call macos_login_items to retrieve information from Velociraptor MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the tool name, this likely retrieves/queries macOS login items (startup programs), which is a read operation. The empty description lowers confidence. Given the server context of digital forensics and incident response, this fits artifact collection/read operations. Severity is medium because login item data can reveal sensitive persistence mechanisms, though the action itself is non-destructive.
From the tool's definition Tool name 'macos_login_items' suggests reading macOS login items; description is empty and uninformative.
Attacks that exploit this kind of access
macos_login_items. It is categorised as a Read tool in the Velociraptor MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Velociraptor MCP Server MCP server in PolicyLayer and add a rule for macos_login_items: 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 Velociraptor MCP Server. Nothing to install.
macos_login_items 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 macos_login_items 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 macos_login_items. 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.
macos_login_items is provided by the Velociraptor MCP Server MCP server (snoe-findley/mcp-velociraptor). 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 →