AI agents invoke xcode_open_project to trigger actions in Xcode. 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.
This tool uses osascript (Apple Script execution) to trigger an external application action (opening Xcode). It runs a script/command to interact with an external process, making it Execute category. The blast radius is medium — it launches Xcode with a specified project, which could expose project contents or trigger Xcode's automatic actions, but doesn't directly modify or delete data.
From the tool's definition Open .xcodeproj or .xcworkspace in Xcode via osascript
Attacks that exploit this kind of access
Open .xcodeproj or .xcworkspace in Xcode via osascript. It is categorised as a Execute tool in the Xcode MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Xcode MCP server in PolicyLayer and add a rule for xcode_open_project: 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 Xcode. Nothing to install.
xcode_open_project 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 xcode_open_project 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 xcode_open_project. 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.
xcode_open_project is provided by the Xcode MCP server (raunaksplanet/xcode-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 →