refresh_project

THE RISK

High Risk

Why refresh_project needs a policy

This tool executes a project-wide parsing operation using libclang. It is not a simple read (it actively re-parses and updates internal state), not purely destructive, and not write in the traditional sense. The blast radius is medium — misuse could cause performance issues or stale state, but it doesn't delete or modify source files.

From the tool's definition 'Manually refresh/re-parse project files to detect changes' — triggers an active re-parsing operation across the codebase

Documented attack patterns abuse exactly the kind of access refresh_project gives an agent:

POLICY

How to control refresh_project

PolicyLayer is an MCP gateway — it sits between your AI agents and C++ MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for refresh_project:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "refresh_project": {
      "limits": [
        {
          "counter": "refresh_project_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

refresh_project stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register C++ MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More C++ MCP Server tools

Write set_project_directory Set the project directory to analyze (use this first before other commands) Read find_callees Find all functions called by a specific function Read find_callers Find all functions that call a specific function Read find_in_file Search for symbols within a specific file Read get_call_path Find call paths from one function to another Read get_class_hierarchy Get complete inheritance hierarchy for a C++ class Read get_class_info Get detailed information about a specific class Read get_derived_classes Get all classes that inherit from a given base class

All 14 C++ MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in C++ MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about refresh_project

What does the refresh_project tool do? +

Manually refresh/re-parse project files to detect changes. It is categorised as a Execute tool in the C++ MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on refresh_project? +

Register the C++ MCP Server MCP server in PolicyLayer and add a rule for refresh_project: 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++ MCP Server. Nothing to install.

What risk level is refresh_project? +

refresh_project is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit refresh_project? +

Yes. Add a rate_limit block to the refresh_project 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 refresh_project completely? +

Set action: deny in the PolicyLayer policy for refresh_project. 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 refresh_project? +

refresh_project is provided by the C++ MCP Server MCP server (kandrwmrtn/cplusplus_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every C++ MCP Server tool call.

Start from C++ MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →