Discover Bazel watchOS application and unit test targets.
AI agents call bazel_watchos_discover_targets to retrieve information from XcodeBazelMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs target discovery by querying the Bazel build system for watchOS-specific targets. It retrieves information about available build targets without side effects, making it a Read operation. The severity is low because discovering build targets poses minimal risk even if misused by an AI agent—it only reveals existing project structure and cannot modify or execute code.
From the tool's definition The tool name contains 'discover' and the description states it 'Discover[s] Bazel watchOS application and unit test targets', which indicates querying/listing existing build targets without modifying, executing, or deleting anything.
Documented attack patterns abuse exactly the kind of access bazel_watchos_discover_targets gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and XcodeBazelMCP, and nothing reaches the server without passing your rules. This is the rule we recommend for bazel_watchos_discover_targets:
{
"version": "1",
"default": "deny",
"tools": {
"bazel_watchos_discover_targets": {}
}
}bazel_watchos_discover_targets is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Discover Bazel watchOS application and unit test targets. It is categorised as a Read tool in the XcodeBazelMCP MCP Server, which means it retrieves data without modifying state.
Register the XcodeBazel MCP server in PolicyLayer and add a rule for bazel_watchos_discover_targets: 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 XcodeBazelMCP. Nothing to install.
bazel_watchos_discover_targets 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 bazel_watchos_discover_targets 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 bazel_watchos_discover_targets. 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.
bazel_watchos_discover_targets is provided by the XcodeBazel MCP server (xcodebazelmcp/xcodebazelmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from XcodeBazelMCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
117 XcodeBazelMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.