three.ws 3D Studio (free)
Server Details
Free text/image → 3D: generate, rig, avatar-ify, and refine GLB models. No auth, no payment.
- Status
- Healthy
- Uptime
- 99.7% over 55 days
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- Repository
- nirholas/three.ws
- GitHub Stars
- 23
TDQS
Scored across 14 tools
Several generation tools overlap heavily: forge_free, mesh_forge, text_to_avatar, and forge_avatar all produce GLBs, with only subtle distinctions (objects vs characters vs rigged). rig_mesh vs forge_avatar also blur since both yield rigged avatars. check_job is clearly distinct, though.
Mixed conventions: verb_noun snake_case for most (check_job, create_agent_persona, search_catalog, refine_model), but noun-first phrasing appears in mesh_forge and forge_free/forge_avatar, plus look_at_model breaks the verb_noun feel. Still readable overall.
14 tools is well within the reasonable range for a generation plus catalog plus persona studio. Each tool maps to a plausible step, though the four overlapping generators feel redundant rather than each earning a distinct slot.
The surface covers generation, rigging, refinement, inspection, catalog discovery, code emission, and a persona lifecycle (create/get/say). Minor gap around persona management (no list or delete persona) but core workflows are well covered.
Available Tools
15 toolscheck_jobCheck a pending 3D generationInspect
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 the user is waiting to see the finished model; for quiet polling on a schedule call get_job instead.
| Name | Required | Description | Default |
|---|---|---|---|
| job_id | Yes | The job_id (or jobId) a pending generation returned. | |
| refine | No | Optional: the refine object a pending refine_model result carried. Pass it back unchanged so the finished model joins that version history. |
create_agent_personaSave a rigged model as a living, persistent agent bodyInspect
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. No sign-in required.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | A display name for the persona, 1–80 characters. | |
| voice | No | Optional voice name to speak with (used for audio-driven lip-sync when available). | |
| glb_url | Yes | Public https URL of the rigged GLB to embody (e.g. from forge_avatar). | |
| source_prompt | No | Optional: the prompt that generated this body, kept as provenance. |
forge_avatarGenerate a rigged, animation-ready avatarInspect
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. Best for characters; objects are steered to the mesh generator. Renders inline in an interactive 3D viewer. Use this when the user wants a character they can pose or animate.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | No | Description of the character/avatar to generate. | |
| image_url | No | Optional http(s) URL to a reference image to reconstruct in 3D. | |
| idempotency_key | No | Optional retry key. Send the same key again (same caller, same arguments, within 24 hours) and you get the original job back instead of a second generation, so a retry after a timeout cannot burn quota twice. Use a fresh key for each distinct request. A failed attempt is not remembered, so its key can be reused. | |
| allow_non_humanoid | No | Set true to rig a non-humanoid subject anyway (rigging assumes a humanoid figure). |
forge_freeGenerate a 3D model from textInspect
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 for a single object or creature from text; for a posable character call forge_avatar, and to change a model you already made call refine_model.
| Name | Required | Description | Default |
|---|---|---|---|
| tier | No | Detail level: draft (fastest), standard (default), or high (best, slower; may fall back to standard under load). | |
| prompt | Yes | Description of the single object or character to model, e.g. "a friendly round robot mascot, glossy white plastic". | |
| idempotency_key | No | Optional retry key. Send the same key again (same caller, same arguments, within 24 hours) and you get the original job back instead of a second generation, so a retry after a timeout cannot burn quota twice. Use a fresh key for each distinct request. A failed attempt is not remembered, so its key can be reused. |
get_agent_personaReload a persona by id (continuity across sessions)Read-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.
| Name | Required | Description | Default |
|---|---|---|---|
| persona_id | Yes | The persona_id returned by create_agent_persona. |
get_catalog_itemRead one catalog itemRead-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.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Catalog id as `<kind>:<name>` from search_catalog. A bare name is also accepted. |
get_item_sourceGet paste-ready source for a catalog itemRead-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 best; 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.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Catalog id from search_catalog. | |
| framework | No | Which form to emit. Defaults to the recommended one for the item kind. "all" returns every applicable variant. |
get_jobGet the status of a 3D jobInspect
Machine-readable status of a generation that returned "pending". Returns status (queued, running, done, failed, not_found), progress (0 to 1, null when unknown), eta_seconds, and next_check_seconds while it runs; the asset links (viewer_url, glb_url, poster_png_url, embed_html) when done; and a plain error with a remedy when it failed. Safe to call on a schedule: it never starts work and is not counted against the generation quota. Use this to poll a pending job from code or a loop; call check_job with the same job_id when you want the finished model rendered in the inline viewer.
| Name | Required | Description | Default |
|---|---|---|---|
| job_id | Yes | The job_id (or jobId) a pending generation returned. | |
| refine | No | Optional: the refine object a pending refine_model result carried, passed back unchanged. |
look_at_modelLook at a 3D modelRead-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 to check your own work right after generating: 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.
| Name | Required | Description | Default |
|---|---|---|---|
| size | No | Pixel size of each square frame. Default 512. | |
| views | No | Angles to render. Default: three-quarter, front, side, back. | |
| glb_url | Yes | Public https URL of the .glb to look at. |
mesh_forgeGenerate a 3D mesh (art-directed)Inspect
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 for a single object or prop when mesh quality matters most; for characters call text_to_avatar or forge_avatar.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | No | Description of the single object to model. | |
| image_url | No | Optional http(s) URL to a reference image to reconstruct directly. | |
| idempotency_key | No | Optional retry key. Send the same key again (same caller, same arguments, within 24 hours) and you get the original job back instead of a second generation, so a retry after a timeout cannot burn quota twice. Use a fresh key for each distinct request. A failed attempt is not remembered, so its key can be reused. |
persona_saySpeak a reply through a persona: lip-sync + emotion + gestureInspect
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.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | The reply text the agent is saying this turn: drives lip-sync and emotion. | |
| emotion | No | Optional explicit emotion override; omit to auto-detect from the text. | |
| persona_id | Yes | The persona to speak through. |
refine_modelRefine a 3D model by describing a changeInspect
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 instead of a fresh generation when the user wants to change a model they already have.
| Name | Required | Description | Default |
|---|---|---|---|
| glb_url | Yes | http(s) URL of the model to refine (e.g. the glbUrl a previous generation returned). | |
| instruction | Yes | The change to make, in plain language: "make it metallic", "bigger helmet", "add a cape". | |
| parent_index | No | Optional: branch off an earlier version in parent_lineage (its index) instead of the latest. | |
| parent_prompt | No | Optional: the prompt that produced the model being refined, so the change builds on it instead of starting over. | |
| parent_lineage | No | Optional: the lineage array from a previous refine_model result, to extend the same version history. | |
| idempotency_key | No | Optional retry key. Send the same key again (same caller, same arguments, within 24 hours) and you get the original job back instead of a second generation, so a retry after a timeout cannot burn quota twice. Use a fresh key for each distinct request. A failed attempt is not remembered, so its key can be reused. | |
| reference_image_url | No | Optional http(s) image of the current model to anchor the re-generation (image→3D). Omit for text-guided refinement. |
rig_meshRig a 3D model for animationInspect
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 static model; to generate and rig a character in one step call forge_avatar instead.
| Name | Required | Description | Default |
|---|---|---|---|
| glb_url | Yes | http(s) URL to the static GLB mesh to rig. | |
| idempotency_key | No | Optional retry key. Send the same key again (same caller, same arguments, within 24 hours) and you get the original job back instead of a second generation, so a retry after a timeout cannot burn quota twice. Use a fresh key for each distinct request. A failed attempt is not remembered, so its key can be reused. |
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.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Free text over titles, names, tags, and categories, e.g. "wooden chair", "office", "wave". Every word must match somewhere, so start broad. | |
| tag | No | Exact tag from a previous result's facets. | |
| kind | No | Narrow to one library: object (CC0 props), character (rigged humanoids), animation (motion clips). | |
| limit | No | ||
| offset | No | Page offset. Use next_offset from the previous response. | |
| category | No | Exact category from a previous result's facets. |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only/idempotent/non-destructive status, but the description adds meaningful behavior: no account required, no cost, return fields including ids and facets, and the recommended next call. This is richer than the structured hints alone.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Front-loaded with the key value proposition, then scope, return shape, and the generation-vs-catalog workflow. Every sentence contributes without repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description still explains the returned fields and facets, covers the no-auth/no-cost context, and provides the routing step to get_item_source. An agent has enough to select and invoke it correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 83%, so most parameters are already documented. The description reinforces the kind categories and points to facets for category/tag narrowing, but does not add syntax or format detail beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource: search the three.ws ready-made asset catalog. It enumerates the three asset libraries and distinguishes itself from sibling generation tools by positioning catalog search as the pre-generation check.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says when to use it ('before generating anything') and why ('if the catalog already has the prop or character, dropping it in is instant and free where generating one is not'). It also names the follow-up path to get_item_source.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
text_to_avatarGenerate a 3D avatarInspect
Generate a textured 3D avatar (GLB) from a text description or a reference image URL. Best for characters and figures. Renders inline in an interactive 3D viewer. Use this for a character that only needs to be viewed; when it must be posed or animated call forge_avatar instead.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | No | Description of the avatar to generate. | |
| image_url | No | Optional http(s) URL to a reference image to reconstruct in 3D. | |
| idempotency_key | No | Optional retry key. Send the same key again (same caller, same arguments, within 24 hours) and you get the original job back instead of a second generation, so a retry after a timeout cannot burn quota twice. Use a fresh key for each distinct request. A failed attempt is not remembered, so its key can be reused. |
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
7 tool updates
- Changed
forge_avatar1 field changed- added
Input schema / properties / idempotency_keyAdded value: +{ + "description": "Optional retry key. Send the same key again (same caller, same arguments, within 24 hours) and you get the original job back instead of a second generation, so a retry after a timeout cannot burn quota twice. Use a fresh key for each distinct request. A failed attempt is not remembered, so its key can be reused.", + "maxLength": 200, + "minLength": 1, + "type": "string" +}
- Changed
forge_free1 field changed- added
Input schema / properties / idempotency_keyAdded value: +{ + "description": "Optional retry key. Send the same key again (same caller, same arguments, within 24 hours) and you get the original job back instead of a second generation, so a retry after a timeout cannot burn quota twice. Use a fresh key for each distinct request. A failed attempt is not remembered, so its key can be reused.", + "maxLength": 200, + "minLength": 1, + "type": "string" +}
- Added
get_job - Changed
mesh_forge1 field changed- added
Input schema / properties / idempotency_keyAdded value: +{ + "description": "Optional retry key. Send the same key again (same caller, same arguments, within 24 hours) and you get the original job back instead of a second generation, so a retry after a timeout cannot burn quota twice. Use a fresh key for each distinct request. A failed attempt is not remembered, so its key can be reused.", + "maxLength": 200, + "minLength": 1, + "type": "string" +}
- Changed
refine_model1 field changed- added
Input schema / properties / idempotency_keyAdded value: +{ + "description": "Optional retry key. Send the same key again (same caller, same arguments, within 24 hours) and you get the original job back instead of a second generation, so a retry after a timeout cannot burn quota twice. Use a fresh key for each distinct request. A failed attempt is not remembered, so its key can be reused.", + "maxLength": 200, + "minLength": 1, + "type": "string" +}
- Changed
rig_mesh1 field changed- added
Input schema / properties / idempotency_keyAdded value: +{ + "description": "Optional retry key. Send the same key again (same caller, same arguments, within 24 hours) and you get the original job back instead of a second generation, so a retry after a timeout cannot burn quota twice. Use a fresh key for each distinct request. A failed attempt is not remembered, so its key can be reused.", + "maxLength": 200, + "minLength": 1, + "type": "string" +}
- Changed
text_to_avatar1 field changed- added
Input schema / properties / idempotency_keyAdded value: +{ + "description": "Optional retry key. Send the same key again (same caller, same arguments, within 24 hours) and you get the original job back instead of a second generation, so a retry after a timeout cannot burn quota twice. Use a fresh key for each distinct request. A failed attempt is not remembered, so its key can be reused.", + "maxLength": 200, + "minLength": 1, + "type": "string" +}
3 tool updates
- Added
get_catalog_item - Added
get_item_source - Added
search_catalog
1 tool update
- Changed
check_job1 field changed- added
Input schema / properties / refineAdded value: +{ + "additionalProperties": true, + "description": "Optional: the refine object a pending refine_model result carried. Pass it back unchanged so the finished model joins that version history.", + "properties": { + "instruction": { + "maxLength": 500, + "type": "string" + }, + "lineage": { + "items": { + "additionalProperties": true, + "type": "object" + }, + "type": "array" + }, + "parentIndex": { + "minimum": 0, + "type": "integer" + }, + "refKind": { + "enum": [ + "text", + "image" + ], + "type": "string" + } + }, + "type": "object" +}
2 tool updates
- Changed
persona_say1 field changed- changed
Input schema / properties / text / descriptionPrevious value: -"The reply text the agent is saying this turn — drives lip-sync and emotion."New value: +"The reply text the agent is saying this turn: drives lip-sync and emotion."
- Changed
refine_model3 fields changed- changed
Input schema / properties / parent_index / descriptionPrevious value: -"Optional — branch off an earlier version in parent_lineage (its index) instead of the latest."New value: +"Optional: branch off an earlier version in parent_lineage (its index) instead of the latest." - changed
Input schema / properties / parent_lineage / descriptionPrevious value: -"Optional — the lineage array from a previous refine_model result, to extend the same version history."New value: +"Optional: the lineage array from a previous refine_model result, to extend the same version history." - changed
Input schema / properties / parent_prompt / descriptionPrevious value: -"Optional — the prompt that produced the model being refined, so the change builds on it instead of starting over."New value: +"Optional: the prompt that produced the model being refined, so the change builds on it instead of starting over."
1 tool update
- Added
look_at_model
1 tool update
- Added
check_job
9 tool updates
- First observed
create_agent_persona - First observed
forge_avatar - First observed
forge_free - First observed
get_agent_persona - First observed
mesh_forge - First observed
persona_say - First observed
refine_model - First observed
rig_mesh - First observed
text_to_avatar
Related MCP Connectors
Turn text or an image into an animation-ready 3D model (GLB): generate, rig, animate, retexture.
3D avatar/asset foundry: text/image -> rigged, validated, engine-ready GLB via x402.
Generate 3D models from images or text with AI, then retexture or convert them to STL, 3MF or OBJ.
141Free text/image to 3D for Grok Bot, plus your three.ws agents once signed in. Never spends.
15123
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceGenerate 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- AlicenseNot gradedqualityCmaintenanceEnables AI clients to generate 3D models through natural language, including text-to-3D and image-to-3D, with tools for checking balance, refining models, converting formats, and a local 3D viewer that works without external network access.1MIT

Meshy MCP Serverofficial
AlicenseNot gradedqualityAmaintenanceEnables AI agents to create, manage, and download 3D models, textures, images, rigged characters, and animations through natural conversation.12,398 npm50MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.