AI agents call zig_hover 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 and queries metadata about Zig code (type information and documentation) without side effects. It is a read-only language server operation analogous to IDE hover features. No data is created, modified, deleted, or executed. The sibling tools like zig_build would be Execute or higher, but zig_hover itself is purely informational.
From the tool's definition Tool provides 'type information and documentation for a symbol at a specific position' via ZLS, which is a language server providing intelligence/analysis without modifying code or executing build operations.
Attacks that exploit this kind of access
Get type information and documentation for a symbol at a specific position in a Zig 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_hover: 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_hover 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_hover 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_hover. 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_hover 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 →