AI agents call zig_definition 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 retrieves metadata about code structure (symbol definition location) without creating, modifying, deleting, or executing anything. It is a classic language server protocol (LSP) read operation analogous to 'go-to-definition' in IDEs, which only navigates and retrieves information.
From the tool's definition Tool description: 'Go to definition — find where a symbol is defined in a Zig codebase via ZLS'. The action is to find/locate a symbol definition, which is a read-only query operation with no modifications or side effects.
Attacks that exploit this kind of access
Go to definition — find where a symbol is defined in a Zig codebase 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_definition: 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_definition 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_definition 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_definition. 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_definition 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 →