github not yet analyzed

ChiR24/Unreal_mcp

github

A comprehensive Model Context Protocol (MCP) server that enables AI assistants to control Unreal Engine through the native C++ Automation Bridge plugin. Built with TypeScript and C++.

maintainer
ChiR24
license
MIT
first seen
2026-06-01
last seen
2026-06-16
releases · 30d
1
short id

Drift inferred · capture-to-capture

tool count over time

36t
23t
capabilities23 tools
transport stdio · http verified reported listed in the official MCP registry counts 23 tools · 0 res · 0 prompts permission surface via README inference

tools

  • animation_physics

    Animation BPs, skeletons, sockets, physics assets, cloth, vehicles, ragdolls, Control Rig, IK

  • build_environment

    Landscapes, foliage, procedural terrain, lighting, spline roads/rivers/fences

  • control_actor

    Spawn, delete, transform, physics, tags

  • control_editor

    PIE, Camera, viewport, screenshots

  • inspect

    Object Introspection

  • manage_ai

    AI controllers, Behavior Trees, EQS, perception, State Trees, Smart Objects, NavMesh/pathfinding

  • manage_asset

    Assets, Materials, Render Targets, Behavior Trees

  • manage_audio

    Audio Assets, Components, Sound Cues, MetaSounds, Attenuation

  • manage_blueprint

    Blueprints, SCS components, graph editing, UMG widgets, layout, bindings, animations

  • manage_character

    Character creation, movement, advanced locomotion

  • manage_combat

    Weapons, projectiles, damage, melee combat

  • manage_effect

    Niagara, particles, debug shapes, GPU simulations

  • manage_gas

    Gameplay Ability System: abilities, effects, attributes

  • manage_geometry

    Procedural mesh creation and editing with Geometry Script

  • manage_interaction

    Interactables, destructibles, triggers

  • manage_inventory

    Items, equipment, loot tables, crafting

  • manage_level

    Load/save, streaming, lighting

  • manage_level_structure

    Levels, sublevels, World Partition, streaming, data layers, HLOD, volumes

  • manage_networking

    Replication, RPCs, network prediction, sessions, split-screen, LAN/voice, game framework, input mappings

  • manage_pcg

    PCG graph assets, subgraphs, input/sampler/filter/spawner nodes, pin connections, execution, partition grid size, and node settings

  • manage_sequence

    Sequencer, cinematics, bindings, tracks, playback, keyframes

  • manage_tools

    Dynamic tool management (enable/disable at runtime)

  • system_control

    UBT, Tests, Logs, Project Settings, CVars, Python Execution

code evidence
evidence-backed findings quoted directly from the published source artifact — not inferred

this server hasn't been statically analyzed yet (npm/PyPI artifacts only).