AI agents call zig_diagnostics to retrieve information from Zig without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool analyzes and reports diagnostic information about code without modifying files, executing code, or triggering side effects. It is purely informational, similar to a linter or static analysis tool that examines source code and returns results. The lack of any action verbs suggesting modification, deletion, or execution places it firmly in the Read category.
From the tool's definition zig_diagnostics retrieves diagnostics (errors, warnings) for a Zig source file; the description indicates a query operation with 'Get diagnostics' and no modification, deletion, or execution of code.
Attacks that exploit this kind of access
Get diagnostics (errors, warnings) for a Zig source file via ZLS. It is categorised as a Read tool in the Zig MCP Server, which means it retrieves data without modifying state.
Register the Zig MCP server in PolicyLayer and add a rule for zig_diagnostics: 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 Zig. Nothing to install.
zig_diagnostics 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 zig_diagnostics 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 zig_diagnostics. 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.
zig_diagnostics is provided by the Zig MCP server (sadopc/mcp-server-zig). 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 →