init_codebase · Ue Codegraph MCP: Risk & Policy

WHAT IT DOES

What init_codebase does on Ue Codegraph

AI agents invoke init_codebase to trigger actions in Ue Codegraph. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why init_codebase needs a policy

This tool actively scans the filesystem, parses C++ files, and writes extracted data into a local SQLite database. It triggers an external indexing operation whose scope depends on the provided codebase path — potentially scanning large directory trees and writing substantial data.

From the tool's definition 'Register and index a UE source or project codebase. Scans C++ files, extracts symbols, UE macros, call graphs, and include dependencies.'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

init_codebase Rate-limited

init_codebase 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.

View as policy code

policy.json

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

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Ue Codegraph, so you can run agents against it safely.

FAQ

Questions about init_codebase

What does the init_codebase tool do? +

Register and index a UE source or project codebase. Scans C++ files, extracts symbols, UE macros, call graphs, and include dependencies. It is categorised as a Execute tool in the Ue Codegraph MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on init_codebase? +

Register the Ue Codegraph MCP server in PolicyLayer and add a rule for init_codebase: 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 Ue Codegraph. Nothing to install.

What risk level is init_codebase? +

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

Can I rate-limit init_codebase? +

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

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

init_codebase is provided by the Ue Codegraph MCP server (yomenstyle/ue-codegraph-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.