Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

three.ws 3D Studio (free)

REMOTE · THREE.WS · SCANNED SEP 20

Free text/image → 3D: generate, rig, avatar-ify, and refine GLB models. No auth, no payment.

Available components

0 this week 89 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security83
Transport & Reachability100
Schema Quality & AI Usability83
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1918 tokens (~147/item across 13 items; 11 tools + 2 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities73
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
  • Supports UI / widget rendering.Pass
Install

How do I install the three.ws 3D Studio (free) MCP server?

three.ws 3D Studio (free) is a hosted endpoint at https://three.ws/api/mcp-studio, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · three.ws

# add to Claude Code
claude mcp add --transport http nirholas-threews-3d-studio-free 'https://three.ws/api/mcp-studio'
// .cursor/mcp.json
{
  "mcpServers": {
    "nirholas-threews-3d-studio-free": {
      "url": "https://three.ws/api/mcp-studio"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "nirholas-threews-3d-studio-free": {
      "type": "http",
      "url": "https://three.ws/api/mcp-studio"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.nirholas-threews-3d-studio-free]
url = "https://three.ws/api/mcp-studio"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "nirholas-threews-3d-studio-free": {
      "type": "remote",
      "url": "https://three.ws/api/mcp-studio",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add nirholas-threews-3d-studio-free --url 'https://three.ws/api/mcp-studio' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  nirholas-threews-3d-studio-free:
    url: "https://three.ws/api/mcp-studio"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "nirholas-threews-3d-studio-free": {
      "Transport": "http",
      "Url": "https://three.ws/api/mcp-studio"
    }
  }
}
# add to Vellum
assistant mcp add nirholas-threews-3d-studio-free -t streamable-http -u 'https://three.ws/api/mcp-studio'
// mcp.json
{
  "mcpServers": {
    "nirholas-threews-3d-studio-free": {
      "type": "http",
      "url": "https://three.ws/api/mcp-studio"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 13 Sept 26 0
    • Tool “check_job” rewrote its description, which is the text the model reads security
  • 10 Sept 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “create_agent_persona” rewrote its description, which is the text the model reads security
    • Tool “forge_avatar” rewrote its description, which is the text the model reads security
    • Tool “forge_free” rewrote its description, which is the text the model reads security
    • Tool “get_agent_persona” rewrote its description, which is the text the model reads security
    • Tool “persona_say” rewrote its description, which is the text the model reads security
    • Tool “refine_model” rewrote its description, which is the text the model reads security
    • “persona_say” reworded the description of “text” cosmetic
    • “refine_model” reworded the description of “parent_index” cosmetic
    • “refine_model” reworded the description of “parent_lineage” cosmetic
    • “refine_model” reworded the description of “parent_prompt” cosmetic
  • 4 Sept 26 0
    • Tool “persona_say” changed its title: Speak a reply through a persona — lip-sync + emotion + gesture → Speak a reply through a persona: lip-sync + emotion + gesture cosmetic

    1 cosmetic change on this day. Switch on “Show cosmetic changes” to see it.

  • 28 Aug 26 0
    • Schema quality: 1731 → 1905 functional
    • New tool “look_at_model” functional
  • 26 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Aug 26 +1
    • Stability: 0.97 → pass security
  • 23 Aug 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

  • 11 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Probed https://three.ws/api/mcp-studio

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=three.ws CN=WR3,O=Google Trust Services,C=US 30 Aug 2026 28 Nov 2026 RSA 2048 SHA256-RSA 8a354b2948e4d8790a0c10ab9fd90c08
SANs: three.ws, www.three.ws
CN=WR3,O=Google Trust Services,C=US (CA) CN=GTS Root R1,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 RSA 2048 SHA256-RSA 7ff005a91568d63abc22861684aa4b5a
CN=GTS Root R1,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 19 Jun 2020 28 Jan 2028 RSA 4096 SHA256-RSA 77bd0d6cdb36f91aea210fc4f058d30d

Background: What to check on a remote MCP endpoint →

DNSSEC secure

Validation of three.ws. Secure

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
ws. present 36454 8 Verified
three.ws. present 62777 13 Verified
three.ws. Verified address RRset verified with the apex keys
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=63072000; includeSubDomains; preload
content-security-policy base-uri 'self'; object-src 'none'; script-src 'self' 'unsafe-inline' 'unsafe-eval' blob: https://cdn.jsdelivr.net https://cdnjs.cloudflare.com https://unpkg.com https://esm.sh https://ajax.googleapis.com https://s3.tradingview.com https://platform.twitter.com https://3d-agent.vercel.app https://three.ws; worker-src 'self' blob:; frame-ancestors 'self' https://ibm.com https://*.ibm.com https://*.seismic.com; report-uri /api/client-errors
x-content-type-options nosniff
referrer-policy strict-origin-when-cross-origin
permissions-policy accelerometer=(), autoplay=(self), camera=(), display-capture=(), encrypted-media=(self), geolocation=(), gyroscope=(), magnetometer=(), microphone=(), midi=(), payment=(self), serial=(), usb=(), xr-spatial-tracking=(self)

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://three.ws/api/mcp-studio Verified 200
http (plaintext) http://three.ws/api/mcp-studio HTTPS enforced 301 https://three.ws:443/api/mcp-studio
MCP tools · 11 exposed · ~1,615 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
check_job ~103

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.

NameTypeReqDescription
job_idstringyesThe job_id (or jobId) a pending generation returned.

No output schema declared.

No examples provided.

create_agent_persona ~216

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. No sign-in required.

NameTypeReqDescription
glb_urlstringyesPublic https URL of the rigged GLB to embody (e.g. from forge_avatar).
namestringyesA display name for the persona, 1–80 characters.
source_promptstringOptional: the prompt that generated this body, kept as provenance.
voicestringOptional voice name to speak with (used for audio-driven lip-sync when available).

No output schema declared.

No examples provided.

forge_avatar ~151

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.

NameTypeReqDescription
allow_non_humanoidbooleanSet true to rig a non-humanoid subject anyway (rigging assumes a humanoid figure).
image_urlstringOptional http(s) URL to a reference image to reconstruct in 3D.
promptstringDescription of the character/avatar to generate.

No output schema declared.

No examples provided.

forge_free ~148

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.

NameTypeReqDescription
promptstringyesDescription of the single object or character to model, e.g. "a friendly round robot mascot, glossy white plastic".
tierstringDetail level: draft (fastest), standard (default), or high (best, slower; may fall back to standard under load).

No output schema declared.

No examples provided.

get_agent_persona ~86

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 at the start of a conversation when the user returns to a named agent.

NameTypeReqDescription
persona_idstringyesThe persona_id returned by create_agent_persona.

No output schema declared.

No examples provided.

look_at_model ~174

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.

NameTypeReqDescription
glb_urlstringyesPublic https URL of the .glb to look at.
sizeintegerPixel size of each square frame. Default 512.
viewsarrayAngles to render. Default: three-quarter, front, side, back.

No output schema declared.

No examples provided.

mesh_forge ~100

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.

NameTypeReqDescription
image_urlstringOptional http(s) URL to a reference image to reconstruct directly.
promptstringDescription of the single object to model.

No output schema declared.

No examples provided.

persona_say ~144

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. This is the turn-by-turn embodiment hook.

NameTypeReqDescription
emotionstringOptional explicit emotion override; omit to auto-detect from the text.
persona_idstringyesThe persona to speak through.
textstringyesThe reply text the agent is saying this turn: drives lip-sync and emotion.

No output schema declared.

No examples provided.

refine_model ~312

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.

NameTypeReqDescription
glb_urlstringyeshttp(s) URL of the model to refine (e.g. the glbUrl a previous generation returned).
instructionstringyesThe change to make, in plain language: "make it metallic", "bigger helmet", "add a cape".
parent_indexintegerOptional: branch off an earlier version in parent_lineage (its index) instead of the latest.
parent_lineagearrayOptional: the lineage array from a previous refine_model result, to extend the same version history.
parent_promptstringOptional: the prompt that produced the model being refined, so the change builds on it instead of starting over.
reference_image_urlstringOptional http(s) image of the current model to anchor the re-generation (image→3D). Omit for text-guided refinement.

No output schema declared.

No examples provided.

rig_mesh ~98

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.

NameTypeReqDescription
glb_urlstringyeshttp(s) URL to the static GLB mesh to rig.

No output schema declared.

No examples provided.

text_to_avatar ~83

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.

NameTypeReqDescription
image_urlstringOptional http(s) URL to a reference image to reconstruct in 3D.
promptstringDescription of the avatar to generate.

No output schema declared.

No examples provided.

Common questions

What is the three.ws 3D Studio (free) MCP server?

three.ws 3D Studio (free) is an MCP server listed in the public MCP registry as io.github.nirholas/threews-3d-studio-free. Free text/image → 3D: generate, rig, avatar-ify, and refine GLB models. No auth, no payment. This page covers its hosted endpoint (https://three.ws/api/mcp-studio).

Is the three.ws 3D Studio (free) MCP server safe to use?

three.ws 3D Studio (free) scores 89 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the three.ws 3D Studio (free) MCP server expose?

three.ws 3D Studio (free) exposes 11 tools: forge_free, text_to_avatar, mesh_forge, rig_mesh, forge_avatar, and 6 more. Their descriptions and schemas cost roughly 1,615 tokens of context every time the server is loaded.

Does the three.ws 3D Studio (free) MCP server require authentication?

No. We connected to three.ws 3D Studio (free) without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the three.ws 3D Studio (free) MCP server still maintained?

three.ws 3D Studio (free) is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.