What is connect-three-ws-mcp?

A setup guide for connecting an MCP client to three.ws servers. MCP is a standard way for an AI client to discover and call external tools, while three.ws servers provide functions such as 3D generation, avatar data, memory, and agent payments.

Use it to configure Claude Code, Claude Desktop, the Agent SDK, or another MCP client with the appropriate three.ws server.

It avoids relying on an outdated server list and explains which endpoint and authentication method match each goal.

How nirholas/three.ws configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to nirholas/three.ws. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/nirholas/three.ws/main/.agents/skills/connect-three-ws-mcp/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/nirholas/three.ws

Made for: Claude Code.

Or install three-ws-core, the plugin that ships this one along with the rest of its 49 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nirholas/three.ws/connect-three-ws-mcp/github.svg)](https://agentmods.dev/skills/nirholas/three.ws/connect-three-ws-mcp)

Your own site

<a href="https://agentmods.dev/skills/nirholas/three.ws/connect-three-ws-mcp"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/connect-three-ws-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nirholas/three.ws/connect-three-ws-mcp"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/connect-three-ws-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,797 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00133	$0.01797
Opus 5.5	$0.00053	$0.00719
Sonnet 5.5	$0.00027	$0.00359
Haiku 4.5	$0.00013	$0.00180

Measured 14d ago against content hash 60b739152003, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

connect-three-ws-mcp scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

`~/.claude/settings.json` under `mcpServers` when the user wants it on every project.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

when_to_use: The user wants the tools available inside their client rather than shelling out to curl. Start with the free server when no account exists yet. For one-off calls over plain HTTP instead, the 3D skills alread

.agents/skills/connect-three-ws-mcp/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Connect a client to three.ws MCP

three.ws publishes a machine-readable directory of its hosted MCP servers. Fetch it rather than trusting a list in any document, including this one:

curl -s https://three.ws/.well-known/mcp.json

Each entry carries name, endpoint, transport, auth, and its documentation link. As of this writing the directory lists 7 hosted servers over Streamable HTTP, and dozens more install-and-run servers are published on npm under the @three-ws scope and registered in the MCP registry (https://registry.modelcontextprotocol.io/?q=io.github.nirholas).

Which server to add

Goal	Server	Auth
Free text or image to 3D, rigged avatars, talking personas	`https://three.ws/api/mcp-studio`	none
Avatars, glTF validation and inspection, agent data, memory	`https://three.ws/api/mcp`	API key or OAuth
Paid 3D lanes: higher-tier generation, retexture, optimization	`https://three.ws/api/mcp-3d`	OAuth or x402
The agent's custodial wallet: balance, find and pay services, monetize an endpoint	`https://three.ws/api/mcp-agent`	OAuth
Discover and price paid agent services across the network	`https://three.ws/api/mcp-bazaar`	OAuth or x402

Start with the free one. https://three.ws/api/mcp-studio needs no account, no key, and no payment, and it already covers the whole generate-and-rig path. Add the authenticated server only when the user wants their own library, agents, or money.

Claude Code

Project scope, in .mcp.json at the repo root (Claude Code auto-discovers it):

{
  "mcpServers": {
    "three-ws-studio": {
      "type": "http",
      "url": "https://three.ws/api/mcp-studio"
    }
  }
}

With an API key, reference an environment variable rather than pasting the secret into a file that gets committed:

{
  "mcpServers": {
    "three-ws": {
      "type": "http",
      "url": "https://three.ws/api/mcp",
      "headers": { "Authorization": "Bearer ${THREE_WS_MCP_TOKEN}" }
    }
  }
}

Read the full file on GitHub · 156 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

14d ago Changed 60b739152003
1mo ago First seen · 156 lines · 133 tokens per session scan B 66e5b3ef8b1c

Subscribe to this mod's changes

connect-three-ws-mcp is a skill published in the GitHub repository nirholas/three.ws (269 stars, last pushed yesterday), licensed Apache-2.0. It adds 133 tokens to every session and 1,797 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-21.

Building agents LLM animation avatar glTF mcp webgl

connect-three-ws-mcp next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
connect-three-ws-mcpnirholas/three.ws	Skill	269	yesterday	Apache-2.0	B	133	Claude Code
cesiumjsznlgis/opengis-skills	Skill	76	10d ago	MIT	A	93	Claude Code, Codex
decision-avatarellmos-ai/skills	Skill	9	4d ago	MIT	A	49	Claude Code, Codex
sheleg-designssheleg/sheleg-design-skill	Skill	4	4d ago	MIT	A	80	Cursor
p5jsmateaix/mateclaw	Skill	1.2k	yesterday	Apache-2.0	A	20	Claude Code, Codex
threejs-docspledgeandgrow/pledge-skills	Skill	10	3mo ago	MIT	A	112	Claude Code, Codex
3d-website-architectdeveshpunjabi/3d-website-skill	Skill	8	8mo ago	MIT	A	240	Claude Code, Codex

three.ws: Skill for Claude Code