AI agents call xcode_read_file to retrieve information from Xcode without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves file contents without altering data, executing code, or triggering external operations. It is a straightforward query operation that fits the Read category. Severity is low because reading source code has minimal blast radius even if misused by an AI agent—it accesses only data already within the Xcode project.
From the tool's definition Tool name is 'xcode_read_file' and description states 'Read a Swift/ObjC file from the project' — explicitly a read operation with no modification or side effects.
Attacks that exploit this kind of access
Read a Swift/ObjC file from the project. It is categorised as a Read tool in the Xcode MCP Server, which means it retrieves data without modifying state.
Register the Xcode MCP server in PolicyLayer and add a rule for xcode_read_file: 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_read_file 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 xcode_read_file 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_read_file. 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_read_file 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 →