Check whether a C++ header file has correct include guards or #pragma once directives. Detects missing guards, malformed macro names, mismatched #endif comments, and suggests correctly formatted guard macros based on the file path.
AI agents call check_include_guard to retrieve information from C++ Style Guide MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes information about header file structure and compliance with style guidelines. It provides suggestions and reporting on naming conventions for include guards but performs no write, execute, destructive, or financial operations. It is a read-only analysis tool with no side effects beyond returning analysis results.
From the tool's definition Tool performs analysis and checking of existing C++ header file directives ('check whether', 'detects', 'suggests') without modifying or executing code. The description indicates purely static analysis of include guards and pragma directives.
Attacks that exploit this kind of access
Check whether a C++ header file has correct include guards or #pragma once directives. Detects missing guards, malformed macro names, mismatched #endif comments, and suggests correctly formatted guard macros based on the file path. It is categorised as a Read tool in the C++ Style Guide MCP Server MCP Server, which means it retrieves data without modifying state.
Register the C++ Style Guide MCP Server MCP server in PolicyLayer and add a rule for check_include_guard: 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 C++ Style Guide MCP Server. Nothing to install.
check_include_guard 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 check_include_guard 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 check_include_guard. 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.
check_include_guard is provided by the C++ Style Guide MCP Server MCP server (songjiangzhou/cpp_guidelines_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 →