Resolve a build and return build identity plus issue counts from Xcode Cloud.
AI agents call get_build_issues to retrieve information from Xcode Cloud without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries build state and issue metadata from Xcode Cloud without modifying, executing, or deleting anything. It has no side effects beyond retrieving information. The blast radius of misuse is minimal—an AI agent could only view build data, not alter CI/CD workflows or cause damage.
From the tool's definition Tool description states 'Resolve a build and return build identity plus issue counts' — it retrieves and returns build metadata and statistics. The verb 'Resolve' in this context means to look up/fetch build information, not to modify state.
Attacks that exploit this kind of access
Resolve a build and return build identity plus issue counts from Xcode Cloud. It is categorised as a Read tool in the Xcode Cloud MCP Server, which means it retrieves data without modifying state.
Register the Xcode Cloud MCP server in PolicyLayer and add a rule for get_build_issues: 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 Cloud. Nothing to install.
get_build_issues 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 get_build_issues 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 get_build_issues. 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.
get_build_issues is provided by the Xcode Cloud MCP server (thatfactory/xcode-cloud-mcp). 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 →