
blockbench-mcp-overview
Discover and use Blockbench MCP tools, resources, and prompts. Use for capability questions, new-project planning, mode navigation, export, display transforms, Bedrock face materials, or native armature workflows.
- Installs
- 1.1K
- Last 24h
- +10
- Trending rank
- #8839
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/jasonjgardner/blockbench-mcp-project --skill blockbench-mcp-overview- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads blockbench-mcp-overview automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Blockbench MCP Overview
For content changes, load blockbench-use first. The running server's tool list and schemas determine available operations; this source skill can describe tools newer than an installed bundle. Tool status and success text are not a substitute for result inspection.
Discover the Host and Workflow
get_capabilities: include_tools=true
# → blockbench, plugin, project, format, formats, tools, notes
list_modes
# → current_mode, modes[{id, available, selected, ...}]
project may be null. Use exact registered format IDs: Generic Model is normally free. Inspect a prospective format with get_capabilities: format_id="free" without switching projects. Detailed feature flags can be null (unknown); compact listings distinguish true flags and unknown flags. Installed plugin formats are supported through discovery rather than a fixed whitelist in these skills.
When a tool depends on editor state, use list_modes and set_mode: mode_id="<returned ID>", then refresh availability. Animate uses animate, not animation. Changing mode does not change project format.
| Workflow | Tools or guidance |
|---|---|
| Cubes, meshes and groups | Modeling |
| Cube/mesh UVs, texture images, painting and layers | Texturing |
| Group rigs, keyframes, curves and timelines | Animation |
Particle effects, locators and particle keyframes (create_particle_effect, add_locator, manage_particle_keyframes, export_particle_pack) | Particles |
| Normal/height/MER channel materials | PBR materials |
| Generating normal/height/MER maps from a color texture (PyPBR or vgpu, Depth Anything) | Albedo to normal |
| Hytale-specific formats, attachments and visibility | Hytale |
| Native armatures and vertex weights | Armature section below |
| Java item/block display transforms | Display section below |
| Bedrock block face material names | Material-instance section below |
| Undo history and file delivery | Recovery/export sections below |
Inspection and IDs
Prefer find_elements_by_criteria and filter_by_material for targeted questions; use list_outline to understand a hierarchy. Read list_textures and list_materials before referring to existing assets. Names can collide, especially a group and its cube, so retain UUIDs.
place_mesh returns {meshes: [{name, uuid, vertex_keys, face_keys}]}. Component arrays follow input order. Other mesh creators and existing meshes can be inspected with get_mesh_info; its vertices and faces have independent next_offset values. Read to null before mutating. Positions and normals are mesh-local. Reinspect after topology changes or undo/redo. See the modeling skill for executable client-orchestration examples.
get_cube_uv: id="<cube UUID>" reads box/per-face mode, face UVs and effective texture dimensions. set_cube_uv edits those values with format checks. list_textures reports uv_size, bitmap_size, and frame_size; create_texture can set an explicit uv_width/uv_height pair in formats with per-texture UV sizing. Schemas and examples are in the texturing skill.
Resources include projects://{id}, nodes://{id}, textures://{id}, and Hytale-specific resources. Discover resource templates and concrete URIs from the live server instead of inventing IDs. Project exports can also return a live .bbmodel resource link.
A Small Model and Animation
This is tool-call pseudocode for a newly intended Bedrock entity. Confirm the format is registered and the project supports animation first.
create_project: name="robot", format="bedrock"
add_group: name="body", origin=[0, 12, 0]
place_cube: elements=[{name: "torso_geo", from: [-4, 12, -2], to: [4, 24, 2]}], group="body"
create_texture: name="skin", width=64, height=64, fill_color="#808080", layer_name="base"
apply_texture: id="torso_geo", texture="skin", applyTo="all"
idle = create_animation: name="idle", animation_length=2, loop=true, bones={}
manage_keyframes: animation_id=idle.uuid, action="create", bone_name="body",
channel="rotation", keyframes=[
{time: 0, values: [0, 0, 0]},
{time: 1, values: [0, 5, 0]},
{time: 2, values: [0, 0, 0]}
]
animation_timeline: animation_id=idle.uuid, action="set_time", time=1
capture_screenshot
Bind idle.uuid to the returned value; it is not a literal tool argument. Inspect UVs before adding detailed texture art. A rest-pose screenshot alone does not verify motion.
Native Armatures
When the running format supports armature_rig, discover the native armature tools: list_armatures, get_armature, add_armature, list_armature_bones, get_armature_bone, add_armature_bone, and the update/remove operations. ArmatureBones and group-based BoneAnimators are different APIs; the general animation tools resolve groups.
For an existing mesh and armature, inspect get_mesh_info for runtime vertex keys and get_vertex_weights: mesh_id="<UUID>" for current weights. set_vertex_weights_batch takes bone_id, mesh_id, and weights: { "<vertex key>": 0.5 }; weights are 0–1. Inspect all contributing weights and deformation at joints after changes; setting one bone's values does not establish a correctly bound or normalized whole rig. Check exporter support for the native rig before promising a skinned runtime asset.
Java Display Transforms
For formats supporting display_mode:
get_display_transform: slot="gui"
set_display_transform: slot="gui", rotation=[30, 225, 0], scale=[0.75, 0.75, 0.75]
enter_display_mode: slot="gui"
capture_screenshot
Display transforms change exported data. Confirm the requested hand, inventory, ground or frame views with their corresponding slots; do not use a camera adjustment to imply those transforms were authored.
Bedrock Block Material Instances
In bedrock_block, get_face_material_instances reads and set_face_material_instance writes names mapped by the target's minecraft:material_instances component.
get_face_material_instances: cube_id="block_geo"
set_face_material_instance: cube_id="block_geo", faces=["up"], material_name="top"
The tools assign face names; they do not create the behavior-pack block components or resource-pack texture definitions. These material instances are separate from PBR texture groups and GPU instancing. Follow material-instance and texture delivery for multiple materials or cutout panels, and the appearance/performance plan before using textures to replace repeated geometry. Entities use client-entity/render-controller bindings rather than this block component. Inspect the geometry export and accompanying target configuration.
Recovery
save_checkpoint inserts a history marker. It does not save a file, preserve an existing redo branch, or make unrecorded script mutations undoable. Use get_undo_stack to locate the marker and count actual entries before undo: steps=N; a paint tool may create multiple native strokes. Preserve intervening user edits.
Use dedicated undo / redo rather than trigger_action for those operations. Direct risky_eval scripts must manage native undo aspects and failure cleanup for mutations. Prefer available dedicated tools and follow the session's existing authorization.
Export
list_export_formats
# Inspect available, has_compile, extension and belongs_to_current_format
export_model: codec_id="project", result_format="embedded"
export_model: codec_id="project", path="C:/models/robot.bbmodel", max_content_length=0
Use an authorized destination on the Blockbench host. Filesystem permission may be handled by the host. only_current_format=true filters the codec listing; use the full listing to discover other available compatible exports.
export_model invokes a codec's compile operation. It does not automatically run the codec's interactive export flow, write all external images, or export separate animation files. Inspect byte_length, output path, truncation and returned content/resource metadata. A truncated text/base64 preview is not a complete downloadable asset. Embedded results contain a complete file only when it fits the response limit.
Select format, dependencies and destination checks using format and delivery guidance. Reopen a copy or inspect the destination app when available; report verification limits accurately.
FAQ
What does the blockbench-mcp-overview skill do?
Discover and use Blockbench MCP tools, resources, and prompts. Use for capability questions, new-project planning, mode navigation, export, display transforms, Bedrock face materials, or native armature workflows.
How do I install blockbench-mcp-overview?
Run npx skills add https://github.com/jasonjgardner/blockbench-mcp-project --skill blockbench-mcp-overview in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/blockbench-mcp-overview/ (personal) or .claude/skills/blockbench-mcp-overview/ (project).
Which AI agents can use blockbench-mcp-overview?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is blockbench-mcp-overview safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains blockbench-mcp-overview?
It is published by jasonjgardner in jasonjgardner/blockbench-mcp-project. It has 1,112 recorded installs.
More from jasonjgardner/blockbench-mcp-project
blockbench-modeling
jasonjgardner/blockbench-mcp-project
Create and edit 3D models in Blockbench using MCP tools. Use when building geometry with cubes, creating meshes, placing spheres/cylinders, editing vertices, extruding faces, or organizing models with groups. Covers both cube-based Minecraft modeling and freeform mesh editing.
blockbench-texturing
jasonjgardner/blockbench-mcp-project
Create and paint textures in Blockbench using MCP tools. Use when creating textures, painting on models, using brush tools, filling colors, drawing shapes, applying gradients, managing texture layers, or working with UV mapping. Covers pixel art texturing, procedural painting, and UV manipulation.
blockbench-animation
jasonjgardner/blockbench-mcp-project
Create and manage animations in Blockbench using MCP tools. Use when animating 3D models, creating keyframes, managing bone rigs, editing animation curves, or working with animation timelines. Covers walk cycles, idle animations, combat animations, and complex multi-bone animations.
blockbench-use
jasonjgardner/blockbench-mcp-project
Load before Blockbench MCP calls that create, modify, or export content. Discover the active format and tools, route to modeling, UV/texturing, animation, particle, PBR, or Hytale guidance, and verify the requested result.
blockbench-pbr-materials
jasonjgardner/blockbench-mcp-project
Create and manage PBR materials in Blockbench using MCP tools. Use for Bedrock textureset.json import/export, normal or height maps, packed MER textures, material channel replacement, and uniform material properties.
blockbench-hytale
jasonjgardner/blockbench-mcp-project
Create Hytale models and animations through Blockbench MCP. Use for character/attachment or prop formats, UV density, stretch, quads, shading, attachment pieces, and visibility keyframes. Requires the Hytale Models plugin.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available