// SCAN REPORT

Ue Codegraph

16 tools. 2 can modify or destroy data without limits.

2 write tools that can modify data. Rate limits recommended.

Last updated: 3 Jul 2026

2 can modify or destroy data

14 read-only

16 tools total

Community server · catalogue entry verified 03/07/2026

How to control Ue Codegraph ↓

TOOL MAP

What Ue Codegraph exposes to your agents

Read (14) Write / Execute (2) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Ue Codegraph tools

Execute · High init_codebase This tool actively scans the filesystem, parses C++ files, and writes extracted data into a local SQLite database. Write · Medium reindex_file This tool modifies the local SQLite database by updating the index for a specific file.

2 of Ue Codegraph's 16 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Ue Codegraph

PolicyLayer is an MCP gateway — it sits between your AI agents and Ue Codegraph, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "reindex_file": {
    "limits": [
      {
        "counter": "reindex_file_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_class": {
    "limits": [
      {
        "counter": "analyze_class_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Ue Codegraph — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON UE CODEGRAPH →

Instant setup, no code required.

FULL CATALOGUE

All 16 Ue Codegraph tools

EXECUTE 1 tools

Execute init_codebase Register and index a UE source or project codebase. Scans C++ files, extracts symbols, UE macros, call graphs,

WRITE 1 tools

Write reindex_file Re-index a single file (useful after file changes).

READ 14 tools

Read analyze_class Get detailed analysis of a C++ class including methods, properties, UE macros, inheritance, and Blueprint expo Read find_blueprint_exposed Find all Blueprint-exposed functions and properties across the codebase. Read find_call_chain Find the shortest call chain from one function to another using recursive CTE graph traversal. Read find_callees Find all functions called by a specific function. Read find_callers Find all functions that call a specific function. Read find_references Find all references to a symbol (class, function, variable) across the codebase. Read find_ue_macros Search for UE macros (UCLASS, UPROPERTY, UFUNCTION, etc.) with optional filtering by type and specifiers. Read get_blueprint_interface Get the complete Blueprint interface for a class (all BP-exposed functions, properties, events, delegates). Read get_class_hierarchy Get the inheritance hierarchy for a class (ancestors, descendants, or both). Read get_file_dependencies Get include dependency graph for a file (what it includes and what includes it). Read get_index_status Get the indexing status and statistics for registered codebases. Read get_macro_specifiers Get all specifiers for a specific UE macro instance, including meta specifiers. Read search_code Search through indexed code using text pattern matching. Read search_symbols Search for symbols using full-text search (FTS5). Supports fuzzy matching.

FAQ

Questions about Ue Codegraph

How do I prevent bulk modifications through Ue Codegraph? +

The Ue Codegraph server has 1 write tools including reindex_file. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Ue Codegraph.

How many tools does the Ue Codegraph MCP server expose? +

16 tools across 1 categories: Read. 14 are read-only. 2 can modify, create, or delete data.

How do I enforce a policy on Ue Codegraph? +

Register the Ue Codegraph MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Ue Codegraph tool call.

Deterministic rules across all 16 Ue Codegraph tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON UE CODEGRAPH →

Instant setup, no code required.

16 Ue Codegraph tools catalogued and risk-classified — across an index of 43,000+ MCP servers.