// SCAN REPORT

Unreal Editor

11 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 2 Jul 2026

1 can modify or destroy data

10 read-only

11 tools total

Community server · catalogue entry verified 02/07/2026

How to control Unreal Editor ↓

TOOL MAP

What Unreal Editor exposes to your agents

Read (10) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Unreal Editor tools

Execute · High trigger_build The tool executes a build process in Unreal Engine, which is a code compilation operation with side effects (generating binaries, modifying build artifacts, potentially invoking post-build steps).

1 of Unreal Editor's 11 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Unreal Editor

PolicyLayer is an MCP gateway — it sits between your AI agents and Unreal Editor, and nothing reaches the server without passing your rules. These are the rules we recommend:

Cap read operations

{
  "get_build_errors": {
    "limits": [
      {
        "counter": "get_build_errors_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Unreal Editor — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON UNREAL EDITOR →

Instant setup, no code required.

FULL CATALOGUE

All 11 Unreal Editor tools

EXECUTE 1 tools

Execute trigger_build Start a build. Default: Live Coding (requires editor running).

READ 10 tools

Read get_build_errors Get parsed build errors from the latest build. Read get_build_status Get build status. Latest build if no ID given. Read get_build_summary Overview of the latest build: error count, warning count, duration. Read get_crash_context Get crash context: last Fatal log entries and crash report directory info. Read get_log_categories List all active log categories with their message counts. Read get_log_stats Summary: errors/warnings per category, most active categories. Read get_recent_logs Get recent log lines, optionally filtered by category and/or severity. Read search_build_output Regex search across raw build output from the latest build. Read search_logs Regex search across the current session log buffer. Read tail_log Get log output from the last N seconds.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Unreal Editor

Is the Unreal Editor MCP server safe to use without restrictions? +

The Unreal Editor server is primarily read-only with 10 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Unreal Editor MCP server expose? +

11 tools across 2 categories: Execute, Read. 10 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on Unreal Editor? +

Register the Unreal Editor MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Unreal Editor tool call.

Deterministic rules across all 11 Unreal Editor tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON UNREAL EDITOR →

Instant setup, no code required.

11 Unreal Editor tools catalogued and risk-classified — across an index of 43,000+ MCP servers.