AI agents invoke xctrace_import to trigger actions in Xctools. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The xctrace tool is Apple's command-line performance tracing utility. An 'import' subcommand typically ingests trace data into Instruments/xctrace, which is an operation that runs the xctrace binary and processes/writes data. Given the empty description, confidence is reduced. Based on the tool name and server context, this likely executes xctrace with import arguments, placing it in the Execute category.
From the tool's definition Tool name 'xctrace_import' on a server described as providing access to 'xctrace for building, testing, and analyzing projects'; description is empty.
Attacks that exploit this kind of access
xctrace_import. It is categorised as a Execute tool in the Xctools MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Xctools MCP server in PolicyLayer and add a rule for xctrace_import: 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 Xctools. Nothing to install.
xctrace_import is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the xctrace_import 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 xctrace_import. 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.
xctrace_import is provided by the Xctools MCP server (nzrsky/xctools-mcp-server). 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 →