Godot MCP Runtime vs Unreal AI Connection
A side-by-side look at the Godot MCP Runtime and Unreal AI Connection MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Godot MCP Runtime for gaming work as a local process; choose Unreal AI Connection for gaming. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Godot MCP Runtime when
- You need dedicated capabilities in the Gaming domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You want tools like
launch_editor, run_project, attach_project.
Choose Unreal AI Connection when
- You need dedicated capabilities in the Gaming domain.
- Its auth model fits you: No auth required.
- You want tools like
execute_unreal_python, run_python_file, apply_python_to_selection.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Gaming | Gaming |
| Quality signal | 69/100 · Great | 51/100 · Good |
| Install command | Confirmed | Not confirmed yet |
| Transport | Local subprocess (stdio) | — |
| Auth | No auth required | No auth required |
| Pricing | Free | Free |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 93 | 9 |
| Directory activity | 4 views 0 installs 0 upvotes | 4 views 0 installs 0 upvotes |
| Tools | 39 | 80 |
| Full listing | View Godot MCP Runtime | View Unreal AI Connection |
Tools & capabilities
Godot MCP Runtime tools 39
launch_editorOpen the Godot editor GUI for a project for the human user. Use only when the user explicitly asks to "open the editor"; for any agent-driven work, use the headless scene/node tools (add_node, set_node_properties, etc.) instead - the editor cannot be controlled programmatically. Returns plain-text confirmation after spawning the editor process. Errors if projectPath has no project.godot.run_projectSpawn a Godot project as a child process with stdout/stderr captured. Required before take_screenshot, simulate_input, get_ui_elements, run_script, or get_debug_output. Set profiling: true at launch to enable the profiler tools. Use attach_project for one you launched yourself. Verifies MCP bridge readiness before returning success. Returns status with the assigned bridge port. Call stop_project when done. Errors if projectPath is not a Godot project or another session is already active.attach_projectInject the MCP bridge into a Godot process you launch yourself, then wait up to 20s for the bridge to start listening and up to 45s total once it has, so a large project's cold start is absorbed; a port that listens but answers no ping gives up sooner. Call BEFORE Godot launches - Godot reads autoloads only at process start, so a late call returns "bridge did not respond." Recommended pattern: kick off the Godot launch in parallel with this call so the wait absorbs startup. Prefer run_project unless MCP must not spawn Godot. Only one attach session is supported per project at a time (attach mode has no env-var channel, so port and token must be baked into the one shared script); a second attach_project on a project another session already attached to is refused, naming that session. Returns plain-text status with the resolved bridge port. Call detach_project or stop_project when done.detach_projectClear attached-mode runtime state and remove the injected McpBridge autoload. Does NOT stop the manually launched Godot process - that stays running. Use after attach_project when you are done driving the game from MCP. For spawned sessions (run_project), use stop_project instead. Mostly optional now: when the bridge disconnects (you closed Godot), the next runtime tool call probes once and ends the attached session itself, removing the autoload. Calling it afterwards still succeeds idempotently, wording the message to distinguish "an attached session existed and already ended" from "this server never attached to a project". Returns: message confirming detach plus externalProcessPreserved (always true here - that is the point of detach vs stop_project). Errors only when a spawned session is what is active; use stop_project for those.get_debug_outputGet captured stdout/stderr from a spawned Godot project. Use whenever runtime tools fail unexpectedly - script errors, missing nodes, and crash backtraces all surface here. Still works after the process exits or crashes: the session clears itself on exit but the captured logs are retained until stop_project. Requires run_project (not attach_project; attached mode does not capture output). Returns: output/errors (last `limit` lines each, default 200), running (false after exit, null when attached), exitCode after exit, attached:true with empty arrays in attached mode.stop_projectStop the spawned Godot project and clean up bridge state. Call when done with runtime testing, even after a crash, and even if you closed the Godot window yourself: it frees the process slot and clears the flag blocking scene-editing tools. A process that exited on its own already removed the bridge autoload at that moment, and this still succeeds - it reports alreadyExited:true with the exit code and the logs captured before the exit, and leaves a finished profiler capture readable. Attached sessions detach without killing the external process. Returns: message, mode, externalProcessPreserved, alreadyExited, exitCode (already-exited case), and condensed finalOutput/finalErrors (capped at 200); get_debug_output has the full log. Errors only when there is no session and no exited process to report.take_screenshotCapture a PNG of the running viewport. responseMode: preview (default - saves full PNG, returns bounded inline preview at 960x540), full (full inline PNG; use for small text or pixel-level inspection), path_only (saved-path only, no inline image). Saved under .mcp/godot-runtime/screenshots/ (persists after stop_project). Returns: inline image block (full/preview modes), plus path and size of the saved PNG; previewPath/previewSize in preview mode; warnings for non-fatal runtime errors. Errors if no session or bridge times out (default 10000ms).simulate_inputSimulate sequential input in a running project and report what each action did. Action `type`: key, mouse_button, mouse_motion, click_element, action, text, wait. For key/mouse_button/action, omit `pressed` to tap (press+release); set it to hold or release. click_element resolves by node path/name (see get_ui_elements), not visible text. Returns: results[] per action with ok, timing, signals fired, the Control hit, UI `changes` (appeared/disappeared/changed), `watch` samples, and `errors` from input handlers (spawned sessions only). Invalid batches inject nothing; a runtime failure stops the batch and skips the rest.get_ui_elementsWalk the running scene tree and return all Control nodes with positions, sizes, types, and text content. Always call this before simulate_input click_element actions to discover valid element names and paths. Requires an active runtime session (run_project or attach_project). visibleOnly defaults true; pass false to include hidden Controls. filter narrows by class. Returns: elements[] with path/type/rect/visible plus optional text/disabled/tooltip.run_scriptExecute a custom GDScript in the live running project with full scene tree access. Requires an active runtime session. Script must extend RefCounted and define func execute(scene_tree: SceneTree) -> Variant. Return values are JSON-serialized (primitives, Vector2/3, Color, Dictionary, Array, and Node path strings). Use print() for debug output - it appears in get_debug_output, not in the result. In spawned mode, stderr runtime errors escalate to errors (when the script returns null) or surface as warnings. Returns: { success, result, warnings?, tip? } where result is the JSON-serialized return value of execute().list_autoloadsList all registered autoloads in a project with paths and singleton status. Use first when diagnosing headless failures - broken autoloads crash all headless ops, so this tells you what is loaded. No Godot process required (reads project.godot directly). Returns: [{ name, path, singleton }].add_autoloadRegister a new autoload in a project. autoloadPath accepts "res://..." or a project-relative path (auto-prefixed). singleton defaults true (accessible globally by name). No Godot process required. Warning: autoloads initialize in headless mode - a broken script will crash every subsequent headless op; validate before adding. Returns plain-text confirmation with the registered name, path, and singleton flag. Errors if an autoload with the same name already exists; use update_autoload to modify.- +27 more on the listing page
Unreal AI Connection tools 80
execute_unreal_pythonUniversal escape hatch — run arbitrary `unreal.*` Python in the editor's interpreter. Multi-line scripts work.run_python_fileExecute a `.py` file from disk in the editor's Python interpreter.apply_python_to_selectionRun a Python snippet with the editor's current selection bound as `actors` / `assets`.exec_python_persistentPersistent Python session — variables defined in one call survive into the next.reset_python_stateWipe the persistent session's globals.get_project_summaryProject name, engine version, enabled plugins, asset count.find_assetsQuery the asset registry by class + path + name.inspect_assetClass, tags, dependencies, referencers, on-disk size.move_assetMove an asset to a different folder; UE creates a redirector at the source path.rename_assetChange an asset's leaf name in place; UE creates a redirector at the old name.duplicate_assetCopy an asset to a new path.delete_assetDelete an asset; refuses if referenced by other packages unless `force=true`.- +68 more on the listing page
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Godot MCP Runtime
{
"mcpServers": {
"erodenn-godot-mcp-runtime": {
"command": "npx",
"args": [
"-y",
"godot-mcp-runtime"
]
}
}
}
Unreal AI Connection
No confirmed install command for Unreal AI Connection yet — follow the setup steps linked from its listing page rather than a guessed package name.
Frequently asked questions
Godot MCP Runtime is categorized under Gaming and uses a local stdio subprocess. Unreal AI Connection belongs to Gaming and uses an install path we have not confirmed yet. Pick Godot MCP Runtime for gaming work and Unreal AI Connection for gaming.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client. Unreal AI Connection has no confirmed install command yet — follow its own setup instructions.
Godot MCP Runtime is listed as free. Auth: no auth required. Unreal AI Connection is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add erodenn-godot-mcp-runtime and najemwehbe-unreal-ai-connection as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Godot MCP Runtime has a quality signal of 69/100 (Great) with 4 views, 0 installs and 93 GitHub stars. Unreal AI Connection has 51/100 (Good) with 4 views, 0 installs and 9 GitHub stars.