three.ws for Grok
Server Details
Free text/image to 3D for Grok Bot, plus your three.ws agents once signed in. Never spends.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- Repository
- nirholas/three.ws
- GitHub Stars
- 23
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 16 tools
Four tools all mean 'turn text/image into a 3D model' (forge_free, mesh_forge, text_to_avatar, forge_avatar) and their boundaries rest on fuzzy adjectives like 'higher quality mesh' vs 'suited to characters' vs 'free with quality tiers'. Worst of all, check_job and get_job both take a job_id and return status/model, distinguished only by side effects (saving/restarting vs read-only) buried mid-description — an agent will easily grab the wrong one. The persona trio and catalog/docs tools are clean, but the generation and job clusters cause real misselection risk.
Everything is snake_case and most names read as verb_noun (check_job, get_job, rig_mesh, refine_model, search_catalog, create_agent_persona). A handful invert the order with a noun-first or noun-phrase style (persona_say, text_to_avatar, mesh_forge), which is a minor deviation rather than a mixed-convention problem.
16 tools is at the upper edge but the domain genuinely spans generation, job polling, rigging, refinement, personas, catalog lookup and docs search. Each cluster earns its place, though the surface would be tighter if the four generation entry points and the two job tools were consolidated.
The core lifecycle is well covered: search/read catalog assets, generate, inspect visually, refine, rig, promote to a persistent persona, and animate speech, plus job polling and doc search. Gaps are minor — no persona listing or deletion, no job cancellation or history listing, and no separate texture/material editing — all workable around.
Available Tools
16 toolscheck_jobCheck a pending 3D generationAInspect
Check on a 3D generation that returned status "pending" and collect the finished model. Pass the job_id from the pending result. While it is still rendering you get updated timing; call again after the suggested wait. Checking can save the completed model and restart failed work on another provider. When it is done the model renders inline in the interactive 3D viewer. Use this when a generation tool returned status "pending" and you need to collect the finished model.
Inputs: job_id (required), refine.
create_agent_personaSave a rigged model as a living, persistent agent bodyAInspect
Turn a generated GLB into a NAMED, persistent agent body: a "persona" the assistant reuses across turns and across sessions. The model is copied into durable storage so the body survives the source URL expiring, then registered under a stable persona_id. The returned view renders the LIVING body inline: it idles between turns, and persona_say makes it lip-sync and emote a reply. The persona_id is the handle: keep it and pass it to get_agent_persona or persona_say later to bring the exact same body back. Use this once a rigged model should become a recurring character the assistant speaks through. Saving a persona needs a free three.ws account (OAuth sign-in or an API key as the bearer); get_agent_persona and persona_say work without one.
Inputs: name (required), glb_url (required), voice, source_prompt.
forge_avatarGenerate a rigged, animation-ready avatarAInspect
Generate a rigged, animation-ready 3D avatar (GLB) from a single text prompt or a reference image, in one step. Generates the mesh, then auto-rigs it with a humanoid skeleton so it is ready to pose and animate. Made for characters; objects are steered to the mesh generator. Renders inline in an interactive 3D viewer. Use this when the user wants a posable, animation-ready character in one step instead of generating then rigging.
Inputs: prompt, image_url, idempotency_key, allow_non_humanoid.
forge_freeGenerate a 3D model from textAInspect
Turn a text prompt into a textured, downloadable 3D model (GLB), free. Describe a single object, character, or creature; the studio generates an interactive model you can rotate, view, and download. Optional quality tier (draft, standard, high); high is slower and may fall back to standard under load. Renders inline in an interactive 3D viewer. Use this when the user wants a new 3D object, character or creature from a text description.
Inputs: prompt (required), tier, idempotency_key.
get_agent_personaReload a persona by id (continuity across sessions)ARead-onlyIdempotentInspect
Bring back a previously saved persona by its persona_id: the SAME body and identity, in a fresh session. Returns the persona name, its model, the accumulated turn count, and the inline living-body view. Use this when a conversation starts and the user returns to a named agent.
Inputs: persona_id (required).
get_catalog_itemRead one catalog itemARead-onlyIdempotentInspect
Free, no account needed. Read one three.ws catalog item in full by its id from search_catalog (for example "object:adjustable_wrench"): metadata, license, CDN urls, the site links that preview or edit it, related items of the same kind, and which source frameworks get_item_source can emit for it. Use this after search_catalog to inspect one result before you embed it; for paste-ready code call get_item_source instead.
Inputs: id (required).
get_item_sourceGet paste-ready source for a catalog itemARead-onlyIdempotentInspect
Free, no account needed. Returns working code that renders one three.ws catalog item on any site: the web component (pinned to the exact published version with its SRI hash), the tag our own browse grids use, plain three.js with GLTFLoader, or a React component. Motion clips return three.js code that parses the clip JSON and plays it. Omit framework to get the one that fits the item; pass all to get every variant at once. Use this when you are ready to put a catalog item on a page or in an app; call get_catalog_item first if you still need its license or metadata.
Inputs: id (required), framework.
get_jobGet a 3D generation jobAIdempotentInspect
Status of a 3D generation job. Pass the job_id any generation tool returned with status "pending". Returns status (pending, done or failed), phase, progress from 0 to 1, eta_seconds and elapsed_seconds while it runs; when done, the model with its viewer_url, glb_url, poster_png_url and embed_html; when failed, the reason and what to do next. Call it as often as you like: it never starts or repeats a generation. Between calls, wait about the eta_seconds it reports, or 15 seconds when it reports none. Use this when a generation tool returned status "pending" and you need its current status or the finished model.
Inputs: job_id (required), refine.
look_at_modelLook at a 3D modelARead-onlyIdempotentInspect
FREE. See a 3D model instead of just linking to it. Renders the GLB from several angles and returns the frames as images you can actually look at, plus its geometry (triangles, materials, textures) and a plain reading of what those numbers mean. Use it right after generating to check your own work: is the subject complete, is the back finished, is anything melted or fused? Then regenerate naming the fault you saw. Works on any public https .glb, not only ones made here. Use this to visually inspect a GLB for defects before you hand it to the user.
Inputs: glb_url (required), size, views.
mesh_forgeGenerate a 3D mesh (art-directed)AInspect
Generate a textured 3D mesh (GLB) from a text prompt or a reference image URL. In text mode an AI art-director first refines your prompt into an optimized single-subject spec for higher mesh quality. Renders inline in an interactive 3D viewer. Use this when you want a higher quality mesh from a rough prompt or reference image, with the prompt refined for you first.
Inputs: prompt, image_url, idempotency_key.
persona_saySpeak a reply through a persona: lip-sync + emotion + gestureAInspect
Make a persona PERFORM a reply: the body lip-syncs the text and shows the matching facial expression and body gesture. Pass the persona_id and the exact text the agent is saying this turn; the emotion is detected from the text automatically (or set it explicitly). The returned view animates the body for this turn: show it alongside the reply. Use this whenever the persona speaks, on every turn, with the persona_id from create_agent_persona or get_agent_persona.
Inputs: text (required), persona_id (required), emotion.
refine_modelRefine a 3D model by describing a changeAInspect
Iterate on a model you already generated: just describe the change in words ("make it metallic", "bigger helmet", "add wings"). The studio re-generates a new version anchored to the previous one, carrying its form and materials forward. Pass the previous model's glb_url and, when you have it, the prompt that made it (parent_prompt) so the change builds on it. Each refinement is recorded as a new version in a lineage you can revert to or branch from, and the returned lineage drives a version strip in the viewer. Renders the new version inline in the interactive 3D viewer. Use this when the user wants to change a model you already generated instead of starting over.
Inputs: glb_url (required), instruction (required), parent_index, parent_prompt, +3 more.
rig_meshRig a 3D model for animationAInspect
Auto-rig a static 3D model (GLB) into an animation-ready model: adds a humanoid skeleton and skin weights so it can be posed and animated. Provide the GLB URL of a model (e.g. one generated by the other tools). Renders the rigged result inline in an interactive 3D viewer. Use this when you already have a GLB and want it rigged so it can be posed and animated.
Inputs: glb_url (required), idempotency_key.
search_catalogSearch the three.ws asset catalogARead-onlyIdempotentInspect
Free, no account needed. Search every ready-made asset three.ws publishes in one call: CC0 3D props and objects, rigged humanoid characters, and retargetable motion clips. Returns ids, titles, tags, licenses, and CDN urls, plus category facets to narrow the next query. Use this before generating anything: if the catalog already has the prop or character, dropping it in is instant and free where generating one is not. Feed a returned id to get_item_source for code that renders it on any site.
Inputs: q, tag, kind, limit, +2 more.
search_docsSearch the three.ws documentationARead-onlyIdempotentInspect
Free, no account needed. Search the three.ws documentation for the section that answers a question, such as "how do I embed an avatar on my site" or "how does auto-rigging work". Returns the matching sections ranked, each with the page and heading title, a url that opens the docs reader at that heading, and a snippet from the start of the section. Use this before guessing at an API or a flow; to browse ready-made 3D assets call search_catalog instead.
Inputs: query (required), limit.
text_to_avatarGenerate a 3D avatarAInspect
Generate a textured 3D avatar (GLB) from a text description or a reference image URL. Suited to characters and figures. Renders inline in an interactive 3D viewer. Use this when the user wants a character or figure generated from a text description or a reference image.
Inputs: prompt, image_url, idempotency_key.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Free text/image → 3D: generate, rig, avatar-ify, and refine GLB models. No auth, no payment.
3D avatars, embeds, glTF tools, agent memory, and on-chain agent identity from three.ws.
Turn text or an image into an animation-ready 3D model (GLB): generate, rig, animate, retexture.
Build a real 3D website by chatting: pages, models and text in space, published to a live URL.
Related MCP Servers
AlicenseAqualityBmaintenanceEnables AI agents to create, manage, and download 3D models, textures, images, rigged characters, and animations through natural conversation.2826,720 npm93MIT- AlicenseNot gradedqualityDmaintenanceGenerate 3D models from text or image. Browse 10K+ free 3D models. AI creative platform with API1MIT

GoModelHub 3D MCPofficial
AlicenseAqualityCmaintenanceEnables 3D model generation via natural language, supporting text-to-3D and image-to-3D with remote or local deployment options.3MIT- AlicenseAqualityBmaintenanceEnables agents to generate 3D models from text prompts or reference images, download GLB files, check operation and subscription status, and re-download completed models using a browser login session.182MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.