UnrealGenAIBLOCK
Unreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gemini 3, Grok 4, Alibaba Qwen, Kimi, ElevenLabs TTS, Inworld, OpenRouter, Groq, GLM, Ollama, Local, Meshy, Tripo, Hunyuan3D, Rodin, fal, Dashscope, Seedream. NPC AI, agentic, chat, 3D gen, TTS
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](LICENSE) [](https://discord.com/invite/KBWmkCKv5U)
Usage Examples:
MCP Example:
Claude spawning scene objects and controlling their transformations and materials, generating blueprints, functions, variables, adding components, running python scripts etc.
API Example:
A project called become human, where NPCs are OpenAI agentic instances. Built using this plugin.
Every month, hundreds of new AI models are released by various organizations, making it hard to keep up with the latest advancements.
The "Unreal Engine Generative AI Support Plugin" allows you to focus on game development without worrying about the LLM/GenAI integration layer.
Current Progress:
This plugin will continue to get updates with the latest features and models. Contributions are welcome. For production-ready alternatives with 200+ AI models, guaranteed stability, automated testing, and UE 5.1-5.7+ support, check out the pro plugins below. **This free plugin covers man
452fb40729d5OBSERVED · 2026-09-28Exposed tools (29)
12 read · 16 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
add_component_to_blueprint | write | |
add_component_with_events | write | |
add_function_to_blueprint | write | |
add_input_binding | write | |
add_node_to_blueprint | write | |
add_variable_to_blueprint | write | |
add_widget_to_user_widget | write | |
compile_blueprint | read | |
connect_blueprint_nodes | read | command = { |
connect_blueprint_nodes_bulk | read | |
create_blueprint | write | |
create_game_mode | write | Create a game mode Blueprint, set its default pawn, and assign it as the current scene’s default game mode. |
create_material | write | |
create_project_folder | write | |
delete_node_from_blueprint | destructive | |
edit_component_property | write | |
edit_widget_property | write | |
execute_python_script | write | |
execute_unreal_command | write | |
get_all_nodes_in_graph | read | |
get_all_scene_objects | read | |
get_blueprint_node_guid | read | |
get_files_in_folder | read | |
get_node_suggestions | read | |
handshake_test | write | Send a handshake message to Unreal Engine |
how_to_use | read | Hey LLM, this grabs the how_to_use.md from knowledge_base—it |
spawn_blueprint_actor | read | |
spawn_object | read | |
take_editor_screenshot | read |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | WARN |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- UNDECLARED (6 observation(s))
- Network
- none-observed
- Shell
- UNDECLARED (1 observation(s))
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (15)
exec(f.read())
ChatAPIExamples.uasset
plugin_settings.cpython-311.pyc
unreal_socket_server.cpython-311.pyc
__init__.cpython-311.pyc
actor_commands.cpython-311.pyc
os.remove(screenshot_path)
os.remove(file)
os.remove(file)
os.remove(pid_path)
os.remove(temp_path)
shell use found in code, not declared in the description
delete_node_from_blueprint
Docs/BHDemoGif.gif
Docs/UnrealMcpDemo.gif
Gates applied: no_behavioural_pass.
452fb40729d5full audit observations/trust-audit/mcp-server/prajwalshettydev__unrealgenai.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 |
|---|---|---|---|---|---|
| 2026-09-28 | 452fb40729d5 | BLOCK | D | 69 | first audit |
Questions
What is the UnrealGenAI MCP server?
Unreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gemini 3, Grok 4, Alibaba Qwen, Kimi, ElevenLabs TTS, Inworld, OpenRouter, Groq, GLM, Ollama, Local, Meshy, Tripo, Hunyuan3D, Rodin, fal, Dashscope, Seedream. NPC AI, agentic, chat, 3D gen, TTS
What tools does UnrealGenAI expose?
29 in total: 12 read-only, 16 that write, and 1 that can delete or overwrite (delete_node_from_blueprint). Every one is listed on this page with its risk.
Is UnrealGenAI safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does UnrealGenAI need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (452fb40729d5), read on 2026-09-28. The repository is watched and re-audited when it changes.