Unreal

127 tools. 100 can modify or destroy data without limits.

4 destructive tools with no built-in limits. Policy required.

Last updated:

100 can modify or destroy data
27 read-only
127 tools total

Community server · catalogue entry verified 30/06/2026

How to control Unreal ↓

What Unreal exposes to your agents

Read (27) Write / Execute (96) Destructive / Financial (4)
Critical Risk

The most dangerous Unreal tools

100 of Unreal's 127 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

How to control Unreal

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

Deny destructive operations
{
  "delete_actor": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
{
  "add_actor_binding": {
    "limits": [
      {
        "counter": "add_actor_binding_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "get_actor_components": {
    "limits": [
      {
        "counter": "get_actor_components_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

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

Instant setup, no code required.

All 127 Unreal tools

EXECUTE 33 tools
Execute build_cook_run Full BuildCookRun pipeline — build, cook, stage, package, and optionally deploy/run. This is the primary comma Execute build_graph Execute a BuildGraph XML script for CI/CD automation. Execute build_plugin Build a plugin standalone. Execute build_target Build a C++ target using UnrealBuildTool. Compiles the project Execute call_preset_function Call a function exposed via a Remote Control Preset. Execute clean_project Clean build artifacts for the project. Execute compile_blueprint Compile a Blueprint. Execute content_audit Run content audit to find costly or problematic assets (runs ContentAudit commandlet). Execute cook_content Cook content only (no C++ build). Converts assets to platform-specific format. Execute execute_console_command Run a console command in the Unreal Editor (e.g., Execute execute_python Execute arbitrary Python code in the Unreal Editor Execute generate_lods Generate LODs for a static mesh. Execute package_project Package the project for distribution. Runs build + cook + stage + package. Execute recompile_material Recompile a material after making changes to its graph. Execute reinit_niagara_system Reinitialize a Niagara system on an actor. Execute render_sequence Queue a Movie Render Queue job for a sequence. Execute reset_niagara_system Reset a Niagara system on an actor. Execute run_all_automation_tests Run all automation tests. Execute run_automation_test Run a specific automation test by name. Execute run_automation_tests_by_category Run automation tests matching a category pattern. Execute run_editor_utility_blueprint Run an Editor Utility Blueprint Execute run_editor_utility_widget Run an Editor Utility Widget by asset path. Execute run_gauntlet Launch a Gauntlet test session via UAT. Runs tests in a full game instance. Execute run_map_check Run Map Check validation on the current level. Execute run_stat_command Execute a stat console command (e.g., stat fps, stat unit, stat memory). Execute select_actors Set the editor Execute spawn_niagara_at_location Spawn a Niagara particle system at a world location. Execute spawn_niagara_attached Spawn a Niagara system attached to an actor. Execute start_csv_profiling Start CSV profiling capture for performance regression analysis. Execute start_trace Start an Unreal Insights trace session with selected channels. Execute stop_trace Stop the active Unreal Insights trace session. Execute validate_assets Run data validation on assets in a directory. Execute validate_data Trigger the Data Validation framework on assets.
WRITE 63 tools
Write add_actor_binding Bind an actor to a level sequence for animation. Write add_blueprint_component Add a component to a Blueprint. Write add_blueprint_function Add a custom function to a Blueprint. Write add_blueprint_variable Add a variable to a Blueprint. Write add_graph_node Add a node to a Blueprint Write add_track Add a track to an actor binding in a sequence. Write apply_anim_modifier Apply an animation modifier to an animation sequence. Write apply_material Apply a material to an actor Write connect_graph_nodes Wire two node pins together in a Blueprint graph. Requires the optional C++ plugin. Write connect_material_expressions Wire two material expression nodes together. Write connect_material_property Connect an expression to a material output property (BaseColor, Normal, Metallic, Roughness, etc.). Write consolidate_assets Consolidate duplicate assets — replace references from source assets to a target asset. Write create_anim_blueprint Create an Animation Blueprint for a target skeleton. Write create_anim_montage Create an animation montage from an animation sequence. Write create_blueprint Create a new Blueprint class. Write create_level_sequence Create a new LevelSequence asset for cinematics. Write create_material Create a new material asset. Write create_material_expression Add an expression node to a material Write create_material_function Create a reusable material function. Write create_material_instance Create a material instance from a parent material. Write disable_plugin Disable a plugin in the .uproject file. Requires editor restart to take effect. Write duplicate_actors Duplicate actors by name. Write duplicate_asset Duplicate an asset to a new path. Write enable_plugin Enable a plugin in the .uproject file. Requires editor restart to take effect. Write export_asset Export an asset to an external file format. Write export_sequence_fbx Export a level sequence to FBX. Write fix_redirectors Clean up asset redirectors in the project (runs FixUpRedirects commandlet). Write generate_collision Generate collision for a static mesh. Write generate_lightmap_uvs Generate lightmap UVs for a static mesh. Write generate_project_files Regenerate IDE project files (Visual Studio, Xcode, Rider). Write import_asset Import an external file (FBX, PNG, WAV, etc.) into the project. Write redo Redo the last undone editor action. Write reimport_skeletal_mesh Reimport a skeletal mesh from its source file. Write rename_asset Rename or move an asset. Write resave_packages Bulk resave all packages in the project (runs ResavePackages commandlet). Write save_all Save all dirty (modified) assets. Write save_asset Force save a specific asset. Write sc_checkin Check in file(s) to source control with a description. Write sc_checkout Check out file(s) from source control. Write sc_mark_for_add Mark new file(s) for add in source control. Write sc_revert Revert file(s) in source control. Write set_actor_property Set a property on an actor via the Remote Control API. Write set_actor_tags Set tags on an actor. Write set_actor_transform Set the location, rotation, and/or scale of an actor. Write set_blueprint_property Set a default property value on a Blueprint Write set_data_layer_state Set the state of a data layer (Loaded, Activated, Unloaded). Write set_material_instance_scalar Set a scalar parameter on a material instance. Write set_material_instance_texture Set a texture parameter on a material instance. Write set_material_instance_vector Set a vector parameter on a material instance. Write set_niagara_bool Set a bool parameter on a Niagara component. Write set_niagara_color Set a linear color parameter on a Niagara component. Write set_niagara_float Set a float parameter on a Niagara component. Write set_niagara_vector Set a vector parameter on a Niagara component. Write set_playback_range Set the playback start and end frames of a sequence. Write set_preset_property Set a property value exposed via a Remote Control Preset. Write set_sequence_framerate Set the display frame rate of a sequence. Write set_skeletal_mesh_lod Configure LOD settings on a skeletal mesh. Write set_streaming_source Configure a streaming source component on an actor for World Partition. Write set_viewport_camera Set the editor viewport camera location and/or rotation. Write spawn_actor Spawn a new actor in the current level. Write spawn_blueprint_actor Spawn an instance of a Blueprint class in the level. Write stop_csv_profiling Stop CSV profiling capture and save results. Write undo Undo the last editor action.
READ 27 tools
Read get_actor_components List all components on an actor. Read get_actor_properties Get all properties of an actor by name. Read get_anim_sequence_info Get info about an animation sequence (length, frames, bone data). Read get_asset_info Get detailed metadata for an asset. Read get_asset_references Get the dependency and referencer graph for an asset. Read get_blueprint_info Get Blueprint info: class, variables, functions, components, and graphs. Read get_build_status Parse the last build output and return structured errors, warnings, and progress. Read get_connection_status Check which Unreal Engine transports are currently connected (Remote Control, Python, Plugin Bridge). Read get_loaded_cells Query currently loaded world partition cells. Read get_preset_info Get details of a Remote Control Preset (exposed properties and functions). Read get_preset_property Get a property value exposed via a Remote Control Preset. Read get_sequence_info Get full structure of a level sequence (bindings, tracks, sections). Read get_test_results Get the results of the last automation test run. Read get_undo_history Get the undo/redo transaction history. Read get_viewport_camera Get the current editor viewport camera location and rotation. Read list_actors List all actors in the current level, optionally filtered by class. Read list_assets List assets in a content directory with optional class filter. Read list_automation_tests List available automation tests in the project. Read list_data_layers List all data layers in the current World Partition level. Read list_graph_nodes List all nodes in a Blueprint Read list_material_expressions List all expression nodes in a material. Read list_plugins List installed plugins and their enabled status. Read list_presets List all Remote Control Presets in the project. Read sc_diff Get the diff for a modified file in source control. Read sc_status Query source control status of file(s). Read search_assets Search for assets by name, class, or tag. Read take_screenshot Capture a screenshot of the active editor viewport. Returns the file path of the saved image.

Related servers

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

Questions about Unreal

Can an AI agent delete data through the Unreal MCP server? +

Yes. The Unreal server exposes 4 destructive tools including delete_actor, delete_asset, delete_material_expression. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Unreal? +

The Unreal server has 63 write tools including add_actor_binding, add_blueprint_component, add_blueprint_function. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Unreal.

How many tools does the Unreal MCP server expose? +

127 tools across 4 categories: Destructive, Execute, Read, Write. 27 are read-only. 100 can modify, create, or delete data.

How do I enforce a policy on Unreal? +

Register the Unreal 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 tool call.

Deterministic rules across all 127 Unreal tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Instant setup, no code required.

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

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.