Is Unreal MCP server safe?
- Node.js shell/command execution
- Node.js dynamic code execution
- Dangerous MCP tool capability
unreal-engine-mcp-server is an AI npm_package analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators, though 8 risky constructs are reported for review. It can: dynamic code execution, filesystem read, filesystem write, install time execution, mcp tools detected, network egress and shell execution — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).
unreal-engine-mcp-server 0.6.0-beta-b
Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of Unreal MCP server's authors. Report a false positive.
Behavioral traits
How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.
Findings (8)
The code turns strings into live code at runtime (eval / new Function / exec).
'import subprocess', 'subprocess.', 'os.system', 'exec(', 'eval(','os.system', 'exec(', 'eval(', '__import__', 'with open', 'open(',Why it matters: If those strings aren't fixed and trusted, they become a way to run arbitrary code.
Fix: Avoid evaluating dynamically constructed code; if unavoidable, ensure the input is a trusted constant and never derived from external data.
An MCP tool exposes a powerful capability (files, shell, network, browser, or credentials).
"name": "control_actor",
"name": "control_editor",
"name": "inspect",
"name": "manage_pcg",
Why it matters: Wired into an agent, these grant it real access to your machine — confirm each is required.
Fix: Confirm each powerful tool is required and constrained; broad MCP tools (shell/filesystem/network) grant an agent significant host access.
The component can run operating-system commands or spawn processes.
import { spawnSync } from 'node:child_process';? spawnSync('cmd.exe', ['/d', '/s', '/c', `"${[command, ...args].map((a) => `"${a}"`).join(' ')}"`],: spawnSync(command, args, { stdio: 'inherit', env });? spawnSync('zip', ['-qr', zipPath, basename(pluginDir)], { cwd: dirname(pluginDir), stdio: 'inherit' }): spawnSync('tar', ['-a', '-c', '-f', zipPath, basename(pluginDir)], { cwd: dirname(pluginDir), stdio: 'inherit' });Why it matters: Powerful and often legitimate — confirm the commands aren't built from untrusted input.
Fix: Confirm the command and its arguments are fully controlled and not derived from untrusted input; prefer execFile with an argument array.
The component reads files from disk.
content = fs.readFileSync(filePath, 'utf-8');
Why it matters: Usually legitimate, but worth confirming it can't be steered into reading sensitive files.
Fix: Confirm which files are read and that paths cannot be influenced by untrusted input to reach sensitive locations.
The component writes or deletes files on disk.
fs.rmSync(targetPath, { recursive: true, force: true });Why it matters: Usually legitimate, but worth confirming the paths can't be controlled by untrusted input.
Fix: Confirm which files are written/deleted and that paths cannot be influenced by untrusted input.
package.json has a 'prepare' script (runs on git/local installs and before publishing).
"prepare": "node -e \"const fs=require('fs');(fs.existsSync('dist')&&fs.existsSync('dist/cli.js')&&fs.existsSync('dist/index.js'))||require('child_process').execSync('npm run build',{stdio:'inherit'})\"",Why it matters: Usually a build step, but confirm it doesn't fetch or run remote code.
Fix: Usually a legitimate build step; confirm it only builds and does not fetch or execute remote code.
The component makes outbound network requests.
return (await this.ensureConnected()) ? jsonResource(uri, await fetch()) : disconnectedResource(uri);
Why it matters: Usually legitimate, but confirm the destinations are expected and no sensitive data leaves.
Fix: Confirm the destination hosts are expected and that no sensitive data is sent off-host.
An MCP tool surface (manifest or tool definitions) was found.
const server = new Server(
Why it matters: Just context — review which tools it offers and their permissions.
Fix: Review the declared MCP tools and their permissions.
Check your own component
Run the same evidence-backed scan on any MCP server, agent skill, or package.
Scan your own componentHow we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →