// MCP TOOL REFERENCE

UE TOOLS

22 tools from the Ue MCP Server, categorised by risk level.

// ALL 22 UE TOOLS

READ 1 tools

Read plugins Introspect npm-distributed plugins that contribute actions into other categories. Read-only. Actions: - li...

WRITE 5 tools

Write audio Audio: sound assets, playback, ambient sounds, SoundCues, MetaSounds. Actions: - list: List sound assets. ... Write foliage Foliage painting, types, sampling, and settings. Actions: - list_types: List foliage types in level - get_... Write gas Gameplay Ability System: abilities, effects, attribute sets, cues. Actions: - add_asc: Add AbilitySystemCo... Write networking Networking and replication: actor replication, property replication, net relevancy, dormancy. Actions: - s... Write reflection UE reflection: classes, structs, enums, gameplay tags. Actions: - reflect_class: Reflect UClass. Params: c...

DESTRUCTIVE 12 tools

Destructive animation Animation assets, skeletons, montages, blendspaces, anim blueprints, physics assets. Actions: - read_anim_... Destructive asset Asset management: list, search, read, CRUD, import meshes/textures, datatables. Actions: - list: List asse... Destructive blueprint Blueprint reading, authoring, and compilation. Covers variables, functions, graphs, nodes, components, inte... Destructive demo Neon Shrine demo scene builder and cleanup. Actions: - step: Execute demo step. Params: stepIndex? - clean... Destructive editor Editor commands, Python execution, PIE, undo/redo, hot reload, viewport, performance, sequencer, build pipe... Destructive gameplay Gameplay systems: physics, collision, navigation, input, behavior trees, AI (EQS, perception, State Trees, ... Destructive level Level actors, selection, components, level management, volumes, lights, and splines. Actions: - get_outlin... Destructive material Materials: create, read, parameters, shading, textures, and graph authoring (expression nodes, connections)... Destructive niagara Niagara VFX: systems, emitters, spawning, parameters, and graph authoring. Actions: - list: List Niagara a... Destructive pcg Procedural Content Generation: graphs, nodes, connections, execution, volumes. Actions: - list_graphs: Lis... Destructive statetree StateTree asset editing: read, modify states/tasks/conditions/transitions/bindings/evaluators/global tasks/... Destructive widget UMG Widget Blueprints, Editor Utility Widgets, and Editor Utility Blueprints. Actions: - read_tree: Read w...

EXECUTE 3 tools

Execute flow Run pre-built named sequences for this project. ALWAYS check project(action="get_status") first - its 'flow... Execute landscape Landscape terrain: info, layers, sculpting, painting, materials, heightmap import. Actions: - get_info: Ge... Execute project Project status, config INI files, and C++ source inspection. Actions: - get_status: Check server mode and ...

OTHER 1 tools

Other feedback Submit feedback to improve ue-mcp when native tools fall short and execute_python was used as a workaround....

// RUNNING THIS SERVER

The managed route: connect Ue through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y ue-mcp

// FAQ

How many tools does the Ue MCP server have? +

The Ue MCP server exposes 22 tools across 5 categories: Read, Write, Destructive, Execute, Other.

How do I enforce policies on Ue tools? +

Route the Ue server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Ue tools fall into? +

Ue tools are categorised as Read (1), Write (5), Destructive (12), Execute (3), Other (1). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.