dcc-mcp

Infrastructure skill - application UI observation and scoped action tools for DCC-adjacent workflows. Use ui_control__snapshot, ui_control__find, ui_control__act, ui_control__wait_for, and ui_control__stop_computer_use for DCC UI Control when a host UI state is not exposed through native DCC APIs. Use the separate, operator-granted ui_control__system_operation only for bounded Windows plug-in setup. Prefer DCC-native skills first, then use ui_control as a policy-controlled fallback.

Infrastructure skill - guide developers and agents through creating or modernizing a full DCC-MCP adapter for Nuke, Blender, 3ds Max, Unreal, ZBrush, Houdini, Maya, and custom studio tools. Use when building server, dispatcher, gateway, packaging, and runtime integration. Not for authoring individual SKILL.md tool packages - use dcc-mcp-skills-creator.

Default DCC control skill — connect to and operate live Maya, Blender, Houdini, Photoshop, 3ds Max, Nuke, Unreal, Godot, RenderDoc, Substance 3D, and other DCC apps through structured DCC-MCP tools. Use this skill first whenever the user asks to operate or control something in a DCC app, even when they do not mention DCC-MCP. Interface-specific intent such as clicking a menu, dismissing a dialog, or controlling a window routes to DCC UI Control after structured tools are checked. OpenClaw and other shell agents use dcc-mcp-cli inventory/search/describe/call; MCP-native IDEs use the gateway MCP surface. Not for tasks unrelated to DCC software.

Infrastructure skill - create, validate, scaffold, and review DCC-MCP skills for the dcc-mcp-core ecosystem. Use when authoring SKILL.md, tools.yaml, scripts, groups, prompts, or skill taxonomy. Not for creating a full DCC-MCP adapter repository - use dcc-mcp-creator.

Foundation library for the DCC Model Context Protocol (MCP) ecosystem. Provides Rust-powered action management, skills system, IPC transport, MCP Streamable HTTP server (2025-03-26 spec, with 2025-06-18 and 2025-11-25 awareness), sandbox security, shared memory, screen capture, USD scene support, and telemetry for AI-assisted DCC workflows. Use when working with Maya, Blender, Houdini, 3ds Max, or any DCC MCP integration.

Gateway skill for cross-DCC asset import — search and resolve assets into a validated AssetDescriptor (local path + attribution). Demo source returns static catalog entries; production sources can add download or remote resolution without changing the contract.

Infrastructure skill — scaffold a new marketplace extension package (SKILL.md + tools.yaml + scripts/) with MIT-0 licensing. Use when creating a publishable marketplace entry for any DCC host. Not for editing existing extensions or driving live DCC scenes — use domain skills for that.

Infrastructure skill — publish (register/update) an extension package to a marketplace catalog. Reads the extension's SKILL.md frontmatter, constructs a CatalogEntry, and upserts it into the target marketplace.json. Optionally commits and pushes when the catalog source is a git repository. Use after scaffolding an extension with marketplace-create-extension. Not for installing or searching extensions — use marketplace-install or marketplace-search for that.

Blender reusable light rigs, HDRI/world setup and rotation animation, light grouping, and render-view controls

Blender object manipulation — create, delete, move, rotate, scale and duplicate objects

Blender rigid body, soft body, cloth, collision, force fields, particle systems, constraints, and simulation cache tools

Set up dcc-mcp-blender for an agent or operator: install Blender Python dependencies with Blender's bundled interpreter, generate MCP host configuration, guide the user through enabling the Blender add-on, and run a first live-tool smoke prompt.

Blender rendering — render scenes, run observable background animation jobs, capture viewport images, and configure output

Blender scene assembly — merge .blend files, append/link data blocks, manage view layers and external references

Plan and install downloaded Blender extension or legacy add-on packages

Execute Python code or scripts inside Blender's Python interpreter

Pipeline skill — viewport capture/flipbook plus ROP render settings and render execution through typed, runtime-aware tools. Exports report written_files, elapsed time, and separate error/warning diagnostics without hanging the host. Pair with houdini-camera-light to set up cameras and lights first.

Scene skill — read-only inspection of the active Houdini hip file and node graphs. Use when you need frame range, hip path, object-level nodes, or node details. Not for creating geometry, sims, or exports — use authoring or interchange skills.

Authoring skill — inspect and edit Houdini node parameters, parameter templates, spare parameters, and channel expressions through typed atomic tools. Use instead of arbitrary Python for reading/setting parms, adding spare parms, and managing expressions. For node connections use houdini-node-graph.

Pipeline skill — generic, adapter-owned project and shot/package automation: set/query the project root, tag and read portable asset metadata, validate a scene for missing files / bad output dirs / dirty state / cook errors, collect file dependencies into a manifest (no copying), and export a shot/package manifest (frame range, cameras, output nodes, caches, written files). No dependency on private production services.

Scene-management skill — typed Houdini scene lifecycle (new/open/save with dirty-scene safeguards), selection (get/set/find), camera discovery, and bounding-box queries. Use these atomic tools instead of arbitrary Python for everyday scene navigation and file operations. Not for node authoring (use houdini-nodes) or geometry/transform edits (use houdini-object-ops).

Set up dcc-mcp-houdini for an agent or operator: install Houdini Python dependencies with hython, generate MCP host configuration, guide the user through the Houdini package / 123.py autostart load step, and run a first live-tool smoke prompt.

Pipeline skill — typed timeline, keyframe, channel, and cache-baking tools. Query/set time, FPS and ranges; set/get/delete/list keyframes; inspect channels and expressions; validate bounded transform-loop continuity; export/import channel JSON; bake channels and trigger bounded simulation/cache renders. The canonical timeline API.

Pipeline skill - run file-based Houdini Python automation, manage hip files, set timeline ranges, and build small node chains from structured specs. Use when orchestrating repeatable Houdini tasks. Not for inspecting a scene only.

Synthetic async skill for gateway integration tests. Sleeps for N seconds and reports progress every 500 ms. No actual Maya installation required — uses MayaStandaloneDispatcher.

Set up dcc-mcp-maya for an agent or operator: install Maya Python dependencies with mayapy, generate MCP host configuration, guide the user through loading the Maya plugin, and run a first live-tool smoke prompt.

Pipeline stage — asset discovery and resolution. Search local asset libraries, resolve paths to structured AssetDescriptor records, and surface candidate assets for downstream import. Use before maya-import-to-scene to locate what to import.

Pipeline stage — structured asset import. Consume an AssetDescriptor produced by maya-asset-source and import the asset (FBX, OBJ, USD) into the current Maya scene via cmds.file(). Handles axis/unit conversion, MaterialMode, PlacementHint, and optional target collection grouping. Returns an ImportToSceneResult with the new node list.

Authoring stage - typed Bifrost procedural modeling and graph construction in Maya. Use to create graph shapes or boards, add Bifrost nodes, set input defaults, and connect ports. Not for ordinary Maya DG nodes (maya-node-graph), polygon edits (maya-mesh-ops), or arbitrary Python/MEL (maya-scripting).

Authoring stage — create, assign, query, and manage Lambert / Blinn / surface shader networks. Use for ad-hoc material assignment. For reusable presets and library workflows use maya-material-library; for final rendering use maya-render.

Authoring stage — schema-validated quick path for creating polygon primitives and editing transforms. Use for predictable, agent-driven primitive creation; the parameters are validated by inputSchema and the results carry structured object names. For complex mesh editing use maya-mesh-ops, for materials use maya-materials, and for arbitrary modelling code drop into maya-scripting.

Authoring stage — keyframes, timeline, animation curves, constraint baking, and curve I/O. Use whenever you create or edit time-based motion. Not for rigging setup (maya-rigging), pose library (maya-pose-library), or render output (maya-render).

Domain skill - capture viewports, render scenes to image files, create preview playblasts, configure renderers (Arnold, V-Ray, Scanline), produce HDR/EXR output and multi-pass AOV renders, inspect render settings and statistics, and adjust common render output options in 3ds Max.

Domain skill - import 3D assets (FBX, OBJ, 3DS, USD) into the current 3ds Max scene via the AssetDescriptor or MAXtoA USD procedural contracts. Use when the user wants external geometry or a renderable USD stage in the scene.

Domain skill - inspect, create, edit, and assign 3ds Max materials and bitmap maps on the main thread. Use when authoring Standard, Physical, or PBR-friendly materials, assigning node materials, and reporting texture connections.

Domain skill - inspect timeline settings, query and edit transform keyframes, bake simple animation curves, exchange curve data, and control viewport playback in 3ds Max.

Domain skill - inspect and manage scene objects in the current Autodesk 3ds Max session. Use when the user asks about nodes, cameras, selection, visibility, parenting, grouping, pivots, transforms, scene metadata, or object cleanup.

Domain skill - configure HDR environment lighting, preview materials, and assign renderer-specific materials (Arnold, V-Ray, Scanline) in 3ds Max.

Domain skill — search and resolve assets into validated AssetDescriptor contracts for cross-DCC asset import pipelines. Returns static catalog entries; production sources can layer download helpers or remote resolution without changing the contract.

Agent-facing skill for importing asset descriptors into Autodesk 3ds Max. Use this skill when a contract payload from dcc_mcp_core.asset_import needs to be turned into scene nodes.

Adobe Photoshop MCP setup — stage and load the adobepy UXP bridge, configure clients, and verify the full server connection

Adobe Photoshop document management — open, query, list, and close documents and layers

Adobe Photoshop image operations — create new documents, export, resize canvas, flatten, merge layers

Adobe Photoshop layer operations — create, delete, reorder, duplicate, rename, set opacity/visibility, fill, blend modes

Adobe Photoshop text layer operations — create, edit, style text layers

Execute named Photoshop Actions

Adobe Photoshop Smart Object operations — convert, copy, edit, and replace

Adobe Photoshop adjustment and batch operations — channels and batchPlay

Build installable DCC MCP Unreal plugin archives and package Unreal projects as Windows executables. Use for long-running compilation, cooking, staging, and packaging tasks. Do not use for Automation Test execution or asset export.

Enable, discover, and call Unreal Engine 5.8+ built-in Unreal MCP tools through the DCC MCP gateway. Use when the user asks to set up, include, compare, inspect, or use Epic's official MCP or Toolset Registry capabilities. Not a replacement for DCC MCP on Unreal 4.18-5.7.

Acquire free Fab marketplace content through Unreal Engine's official Fab integration, then verify the imported Content Browser assets. Use when the user asks to find, download, add, or import Fab or Unreal Marketplace assets. Not for arbitrary file imports - use unreal-assets instead.

Domain skill - Unreal Engine Content Browser asset management: list, import, export, inspect, and delete assets. Use for package and asset operations in the Unreal Editor. Not for actor placement or transforms - use unreal-actors for that.

Domain skill - Unreal Engine actor management: list, spawn, transform, and delete level actors. Use when inspecting or editing actors in the current Unreal Editor level. Not for Content Browser asset import/export - use unreal-assets for that.

Domain skill - Unreal Engine native Automation Test and MCP health validation. Use to list UE Automation tests, queue native test runs, and run a safe self-check against the active MCP server.

Domain skill - Unreal Engine level and world management: inspect level state, load and save maps, and read or edit world settings. Use for active Editor level operations. Not for individual actor transform edits - use unreal-actors for that.

Domain skill for authoring and inspecting OpenUSD stages. Create a stage, list prims, define Xform prims, set xform operations (translate/rotate/scale), modify stage metadata (upAxis, metersPerUnit, framesPerSecond), and add reference arcs to external assets. Create portable UsdGeom.Mesh polygon topology and UsdGeom.Points primitives for particles and point-based FX.

Domain skill for creating cameras and lights in an OpenUSD stage. Create UsdGeomCamera, DistantLight, SphereLight, HDR DomeLight, and set transforms or visibility on prims.

Domain skill for USD material authoring. Create UsdShadeMaterial prims, attach PBR UsdPreviewSurface shaders, and bind materials to geometry prims.

Domain skill for animation time samples. Set stage time codes and author translate/rotate/scale samples on Xformable prims as well as arbitrary attribute time samples.

Domain skill for OpenUSD composition arcs. Add sublayers, payloads, variant sets, and variant selections to build multi-layer scenes.

Domain skill for creating and maintaining self-contained OpenUSD project folders with scene.usda, assets, materials, lights, packages, and snapshots. Use before authoring a new OpenUSD stage or when resuming a portable project.

Infrastructure skill for validating OpenUSD stage invariants and packaging a stage into a USDZ-style archive. Use after authoring or before handoff.

Pipeline skill — import OBJ or FBX asset files into ZBrush as subtools. Consumes the dcc-mcp-core asset_import contract (AssetDescriptor) and returns an ImportToSceneResult with the imported subtool names. Use when you need to bring geometry from disk into the active ZBrush scene.

Domain skill — export meshes from ZBrush to interchange formats. Use when you need OBJ export from the active subtool. Not for in-scene sculpt edits — use zbrush-subtool first to pick the correct subtool.

Domain skill — read-only scene and tool introspection for ZBrush. Use when you need active tool path, subtool inventory, or selection index. Not for sculpting, export, or subtool mutation — use zbrush-subtool or zbrush-interchange.

Thin-harness skill — controlled Python execution and session diagnostics inside ZBrush 2026.1+. Use when no typed ZBrush skill covers the task or you need version/subtool counts. Not for routine scene edits — prefer zbrush-scene or domain skills first.

Domain skill — select, inspect, and apply bounded refinement to subtools on the active ZBrush tool. Use when you need to switch the active subtool, read visibility/lock flags, subdivide, polish, or inflate. Not for mesh export or arbitrary Python — use zbrush-interchange or zbrush-scripting.

Infrastructure skill for validating OpenColorIO configs and converting image pixels between named color spaces. Use for consistent film, animation, and game color pipelines.

Infrastructure skill for inspecting images and producing tiled mipmapped renderer textures with OpenImageIO. Use before DCC material binding. Not for creative image generation.

Host skill - inspect and explicitly save the active Katana node graph. Use when checking nodes, selection, and project state. Not for raw Python execution.