Unreal EditorBLOCK
Complete Unreal Engine development toolkit exposed as MCP tools.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://www.npmjs.com/package/ue-mcp) [](https://www.npmjs.com/package/ue-mcp) [](https://github.com/db-lyon/ue-mcp/actions/workflows/ci.yml) [](https://github.com/db-lyon/ue-mcp/stargazers) [](LICENSE)
Unreal Engine Model Context Protocol Server - gives AI assistants deep read/write access to the Unreal Editor through 26 category tools covering 1972+ actions, plus a YAML flow engine for multi-step workflows and an npm plugin system for extending the surface.
That total is 1142+ actions of ue-mcp's own plus Epic's entire native AI Toolset Registry: on UE 5.8+ its 830 official Unreal tools are called in-process and surfaced as epic_* actions in the matching category, Sequencer in animation, PCG in pcg, static meshes in asset.
flowchart LR AI[AI Assistant] -->|stdio| MCP[MCP ServerTypeScript / Node.js] MCP -->|WebSocketJSON-RPC| Plugin[C++ Bridge Plugininside Unreal Editor] Plugin -->|UE API| Editor[Editor Subsystems] MCP -->|direct fs| FS[Config INIC++ HeadersAsset Listing]
Blueprints, materials, levels, actors, animation, VFX, landscape, PCG, foliage, audio, UI, physics, navigation, AI, StateTree, GAS, networking, sequencer, build pipeline - all programmable through natural language.
Filesystem reads (INI config, C++ headers, asset listing) work with the editor closed, so an agent can
5552060af780OBSERVED · 2026-10-06Connect
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. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add ue-mcp --env ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY} --env REGISTRY_PUBLISH_TOKEN=${REGISTRY_PUBLISH_TOKEN} -- npx -y [email protected]{
"mcpServers": {
"ue-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"ANTHROPIC_API_KEY": "${ANTHROPIC_API_KEY}",
"REGISTRY_PUBLISH_TOKEN": "${REGISTRY_PUBLISH_TOKEN}"
}
}
}
}Exposed tools (4)
4 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
after | read | |
before | read | flat |
context_probe | read | asks the context what it is |
flow | read |
Trust audit
BLOCKgrade F · trust 56/100 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 | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (10 observation(s))
- Network
- declared (9 observation(s))
- Shell
- declared (11 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (25)
doc = yaml.load(text);
const raw = yaml.load(fs.readFileSync(file, "utf-8"), { filename: file });const raw = yaml.load(fs.readFileSync(manifestPath, "utf-8")) as unknown;
const m = yaml.load(fs.readFileSync(manifestPath, "utf8")) ?? {};const doc = yaml.load(m[1]);
const proc = exec(fullCommand, {export const DEMO_FLOWS = new Set(["beacon", "neon_shrine", "neon_shrine_cleanup"]);
export const DEMO_PATHS = new Set(["/Game/Flows/Beacon", "/Game/MCP_Home"]);
const PKG = "/Game/Flows/Beacon";
beacon: {.vsconfig
"description": "Folder for the new function (default /Game/Materials/Functions)"
packagePath: z.string().optional().describe("Folder for a new material (default /Game/Materials) (build_material). Folder for the new material (default /Game/Materials) (create_material, create_materireturn new Function("z", `return ${expr};`)(z) as z.ZodTypeAny;const generated = new Function("z", `return ${zodExpression(param)}`)(zodRuntime) as z.ZodTypeAny;const h = crypto.createHash("sha1")const h = crypto.createHash("sha1").update(norm, "utf8").digest();const h = createHash("sha1").update(normalized, "utf8").digest();import type { ActionSpec } from "../../core/types.js";import { bp } from "../../surface/category-tool.js";import { specProblems, paramsClause, formsMessage } from "../../src/surface/handler-spec.js";import { makeSpecBp, type HandlerSpecs } from "../../surface/handler-spec.js";import type { HandlerSpecs } from "../../surface/handler-spec.js";expect([...(DEMO_PATHS as Set<string>)]).toEqual(["/Game/Flows/Beacon", "/Game/MCP_Home"]);
http://127.0.0.1:7723/flows/events
Gates applied: no_behavioural_pass.
5552060af780full audit observations/trust-audit/mcp-server/db-lyon__unreal-editor.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 |
|---|---|---|---|---|---|
| 2026-10-06 | 5552060af780 | BLOCK | F | 56 | first audit |
Questions
What is the Unreal Editor MCP server?
Complete Unreal Engine development toolkit exposed as MCP tools.
What tools does Unreal Editor expose?
4 in total: 4 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Unreal Editor safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (56/100) and found 6 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does Unreal Editor need?
It reads ANTHROPIC_API_KEY and REGISTRY_PUBLISH_TOKEN from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Unreal Editor run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as ue-mcp at 1.3.10-beta.13.
How current is this page?
The grade is for one exact copy of the source (5552060af780), read on 2026-10-06. The repository is watched and re-audited when it changes.