Low Risk

check_const_correctness

Check C++ code for const correctness issues. Identifies member functions that do not modify state but are missing the const qualifier, non-const references where const references would suffice, and variables that are never modified but not declared const. Returns a report with specific locations ...

Risk signalsAccepts freeform code/query input (code)

Part of the C++ Core Guidelines server.

check_const_correctness is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE C++ CORE GUIDELINES →

Free to start. No card required.

AI agents call check_const_correctness to retrieve information from C++ Core Guidelines without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though check_const_correctness only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "check_const_correctness": {}
  }
}

See the full C++ Core Guidelines policy for all 5 tools.

Get this rule live on your own C++ Core Guidelines server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY C++ CORE GUIDELINES →

These attack patterns abuse exactly the kind of access check_const_correctness gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so check_const_correctness only ever does what you allow.

SECURE C++ CORE GUIDELINES →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the check_const_correctness tool do? +

Check C++ code for const correctness issues. Identifies member functions that do not modify state but are missing the const qualifier, non-const references where const references would suffice, and variables that are never modified but not declared const. Returns a report with specific locations and suggested fixes.. It is categorised as a Read tool in the C++ Core Guidelines MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on check_const_correctness? +

Register the C++ Core Guidelines MCP server in PolicyLayer and add a rule for check_const_correctness: 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++ Core Guidelines. Nothing to install.

What risk level is check_const_correctness? +

check_const_correctness is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit check_const_correctness? +

Yes. Add a rate_limit block to the check_const_correctness 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.

How do I block check_const_correctness completely? +

Set action: deny in the PolicyLayer policy for check_const_correctness. 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.

What MCP server provides check_const_correctness? +

check_const_correctness is provided by the C++ Core Guidelines MCP server (SongJiangzhou/cpp_guidelines). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every C++ Core Guidelines tool call.

Deterministic rules across all 5 C++ Core Guidelines tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.