@runreal/unreal-mcp
npm
v0.1.4
Published by @runreal — no publish provenance and no public repository, so the publisher could not be verified and the source cannot be independently located.
MCP server for Unreal Engine using Unreal Python Remote Execution
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 15.4 = 85. What the published surface and source actually contain:
| Points | What was found | Category |
|---|---|---|
| −15.4 | Encoded blob paired with a decode/execute instruction MTC-INJ-ENC-2 | injection |
2. Client adoption risk — 85 − 8 = 77. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
| −2 | publisher verification (unlinked) — no provenance/repo link, but the shipped source was fully read |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
A long base64-looking blob appears alongside a decode/execute instruction — a common way to hide a payload from reviewers.
Evidence: Take a screenshot of the Unreal Editor
Example output: data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAA...
Returns a base64-encoded PNG image of the current edi
Location: tool editor_take_screenshot · description
In the server's implementation (`dist/utils.js:5`): Evaluating a runtime value as code (rather than a fixed literal) executes whatever reaches it — a direct RCE primitive, and almost never necessary in legitimate code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: vars = {}) { return new Function(...Object.keys(vars), `return \`${tmpl}\`;`)(...Object.values(vars)); }
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/utils.js
In the server's implementation (`dist/utils.js:5`): Evaluating strings as code is the most direct RCE primitive; if any tool input reaches it, the server executes attacker-chosen code. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: vars = {}) { return new Function(...Object.keys(vars), `return \`${tmpl}\`;`)(...Object.values(vars)); }
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/utils.js
In a packaging/dev/install script (shipped, but not the server runtime) (`dist/scripts/make-executable.js:15`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: ue: true }); const node_child_process_1 = require("node:child_process"); // https://github.com/modelcontextprotocol/insp
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/scripts/make-executable.js
Each tool and what it can reach — statically extracted from the published source.
editor_console_commandno sensitive capabilityeditor_create_objectno sensitive capabilityeditor_delete_objectno sensitive capabilityeditor_export_assetno sensitive capabilityeditor_get_asset_infono sensitive capabilityeditor_get_asset_referencesno sensitive capabilityeditor_get_map_infono sensitive capabilityeditor_get_world_outlinerno sensitive capabilityeditor_list_assetsno sensitive capabilityeditor_move_camerano sensitive capabilityeditor_project_infono sensitive capabilityeditor_run_pythonno sensitive capabilityeditor_search_assetsno sensitive capabilityeditor_take_screenshotno sensitive capabilityeditor_update_objectno sensitive capabilityeditor_validate_assetsno sensitive capabilityget_unreal_engine_pathno sensitive capabilityget_unreal_project_pathno sensitive capabilityset_unreal_engine_pathno sensitive capabilityset_unreal_project_pathno sensitive capabilityScan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.1.4 latest |
C 77/100 | 4 | 1.13.0 | 2026-09-07 |
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan @runreal/unreal-mcp --online
Uncensored AI tools (chat, image, RE/malware analysis, JS deobfuscation, multi-step research) for Claude Desktop, Cursor, Cline, Zed, and any MCP client.
儿童故事 MCP 服务 - 提供故事列表和搜索功能
Grade any bet against thousands of play-by-play game simulations: win probability, odds, edge.
World Cup MCP server for the 2026 men's football tournament — live scores, fixtures, standings, read-only prediction-market signals, and paste-ready match cards. Works with Claude Code, Cursor, Codex, Windsurf, Zed. Not affiliated with FIFA or Anthropic.
MCP server exposing a live Dwarf Fortress fort to an AI agent as curated, semantic tools
MCP Server for Arknights: Endfield (TypeScript / stdio + Streamable HTTP)