Unreal AnalyzerSAFE
MCP server for Unreal Engine 5
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://mseep.ai/app/ayeletstudioindia-unreal-analyzer-mcp)
A Model Context Protocol (MCP) server that provides powerful source code analysis capabilities for Unreal Engine codebases. This tool enables AI assistants like Claude and Cline to deeply understand and analyze Unreal Engine source code.
Features
- Class Analysis: Get detailed information about C++ classes including methods, properties, and inheritance
- Hierarchy Mapping: Visualize and understand class inheritance hierarchies
- Code Search: Search through code with context-aware results
- Reference Finding: Locate all references to classes, functions, or variables
- Subsystem Analysis: Analyze major Unreal Engine subsystems like Rendering, Physics, etc.
- Game Genre Knowledge: Built-in knowledge base of game genres, features, and implementation patterns
- Pattern Detection & Learning: Identifies common Unreal Engine patterns and provides learning resources
- Custom Codebase Support: Analyze your own Unreal Engine project codebase
Quick Start
Installation
- Clone this repository:
git clone https://github.com/ayeletstudioindia/unreal-analyzer-mcp cd unreal-analyzer-mcp
- Install dependencies:
npm install
- Build the project:
npm run build
Configuration
For Claude Desktop App
Add the following to your Claude desktop configuration file (%APPDATA%\Claude\claude_desktop_config.json on Windows):
{
"mcpServers": {
"unreal-analyzer": {
"command": "node",
"args": ["path/to/unreal-analyzer/build/ind55e5eb3509daOBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add unreal-analyzer -- npx -y [email protected]
{
"mcpServers": {
"unreal-analyzer": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (18)
16 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Action | read | Games focused on physical challenges, including hand-eye coordination and reaction time |
Combat | read | Real-time conflict resolution through physical or projectile-based combat |
Dialog | read | Branching conversation systems and narrative choices |
Inventory | read | Systems for managing items, equipment, and resources |
Movement | read | Complex character movement and traversal mechanics |
RPG | read | Games focusing on character development, storytelling, and strategic decision-making |
Stealth | read | Mechanics for avoiding detection and strategic approach |
Strategy | read | Games emphasizing tactical thinking and resource management |
analyze_class | read | Get detailed information about a C++ class |
analyze_subsystem | read | Analyze a specific Unreal Engine subsystem |
detect_patterns | read | Detect Unreal Engine patterns and suggest improvements |
find_class_hierarchy | read | Get the inheritance hierarchy for a class |
find_references | read | Find all references to a class, function, or variable |
get_best_practices | read | Get Unreal Engine best practices and documentation for a specific concept |
query_api | read | Search and retrieve Unreal Engine API documentation |
search_code | read | Search through code with context |
set_custom_codebase | write | Set the path to a custom C++ codebase for analysis |
set_unreal_path | write | Set the path to Unreal Engine source code |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@modelcontextprotocol/create-server, glob, tree-sitter, tree-sitter-cpp, @types/glob, @types/jest, @types/node, jest
Gates applied: no_behavioural_pass.
55e5eb3509dafull audit observations/trust-audit/mcp-server/ayeletstudioindia__unreal-analyzer.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | 55e5eb3509da | SAFE | B | 89 | first audit |
Questions
What is the Unreal Analyzer MCP server?
MCP server for Unreal Engine 5
What tools does Unreal Analyzer expose?
18 in total: 16 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Unreal Analyzer safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Unreal Analyzer need?
No credential environment variables were found in its source, so it appears to need none.
How does Unreal Analyzer run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as unreal-analyzer at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (55e5eb3509da), read on 2026-10-07. The repository is watched and re-audited when it changes.