three.ws Marketplace

io.github.nirholasPublished by GitHub account nirholasv0.1.3Updated Nov 1, 2026

Browse and discover the public three.ws agent marketplace and skills catalog. Read-only.

VerifiedSTDIODesktop onlyKnowledge & MemoryAI & ML

Overview

AI-generated overview

Read-only MCP server that lets an assistant browse and search the public three.ws agent marketplace and skills catalog.

What you can do
  • Search and page published agents by category, query, sort order and cursor
  • Fetch a single agent's details by id, including prompt, capabilities, author, ratings and skill prices
  • List agent categories with published-agent counts and the overall total
  • Search and page the skills catalog by query and category
  • List skill categories that contain at least one public skill
When to use it
Useful when you want an assistant to discover existing AI agents or reusable skills on three.ws, compare them by rating or popularity, or look up one agent's details before deciding to use it. Not needed if you only work with your own local agents.
Requirements
Node.js 20 or newer, run locally via npx or npm install. Network access to three.ws, or a self-hosted base URL set through THREE_WS_BASE. Optional THREE_WS_TIMEOUT_MS sets the per-request timeout. No API key or account is required.
Before you install
All tools are read-only, so nothing can be published or purchased through this server. Queries and page requests go to the public three.ws API, so search terms are sent to that third party. Pointing THREE_WS_BASE at another host sends your requests there instead.

Installation

In SourceWeft

  1. Open three.ws Marketplace in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

[three.ws]

@three-ws/marketplace-mcp

Browse the three.ws agent marketplace and skills catalog from any AI agent.

[npm] [license] [node] [MCP Registry] [three.ws]


A Model Context Protocol server that gives any AI assistant browse and discovery of the three.ws marketplace over stdio. Search and page the published agents, drill into one by id, and explore the reusable skills catalog — all from the public three.ws API.

No API key, no signer, no payment — every call hits the public /api/marketplace and /api/skills endpoints. Creating or publishing agents and skills is the authenticated write path on the HTTP API; this server exposes browse/discovery only.

Install

bash
npm install @three-ws/marketplace-mcp

Or run with npx (no install):

bash
npx @three-ws/marketplace-mcp

Quick start

Claude Code, one line:

bash
claude mcp add marketplace -- npx -y @three-ws/marketplace-mcp

Claude Desktop / Cursor (claude_desktop_config.json or mcp.json):

json
{	"mcpServers": {		"marketplace": {			"command": "npx",			"args": ["-y", "@three-ws/marketplace-mcp"]		}	}}

Inspect the surface with the MCP Inspector:

bash
npx -y @modelcontextprotocol/inspector npx @three-ws/marketplace-mcp

Tools

ToolTypeWhat it does
browse_agentsread-onlySearch & page the agent marketplace — filter by category and query, sort, paginate by cursor.
agent_detailread-onlyFetch one published agent by id (system prompt, capabilities, author, ratings, skill prices, avatar).
agent_categoriesread-onlyList agent categories with the count of published agents in each, plus the overall total.
browse_skillsread-onlySearch & page the skills catalog — filter by query and category, sort, paginate by cursor.
skill_categoriesread-onlyList skill categories that have at least one public skill, each with a slug, label, and count.

Input parameters

browse_agents — category (optional slug), q (optional free text), sort (recommended | recent | popular | top_rated, default recommended), limit (1–48, default 24), cursor (optional pagination cursor).

agent_detail — id (required: the agent's UUID, from a browse_agents card).

agent_categories — no parameters.

browse_skills — q (optional free text), category (optional slug), sort (popular | new | az, default popular), limit (1–50, default 20), cursor (optional pagination cursor).

skill_categories — no parameters.

Example

jsonc
// browse_agents> { "q": "code review", "sort": "top_rated", "limit": 3 }{  "ok": true,  "items": [    {      "id": "a1b2c3d4-…",      "name": "Code Reviewer",      "description": "Reviews diffs for bugs and style.",      "category": "programming",      "tags": ["code", "review"],      "rating_avg": 4.8,      "rating_count": 22,      "views_count": 1340,      "forks_count": 41,      "thumbnail_url": "https://…",      "avatar_glb_url": "https://…"    }  ],  "next_cursor": "3"}

Pass next_cursor back as cursor to fetch the following page.

Examples

Runnable examples live in examples/:

bash
node examples/list-tools.mjs            # every tool with its full input schemanode examples/browse-marketplace.mjs    # categories + agents + detail + skills, live

Both spawn this server over stdio and read the live public catalog. Every tool here is read-only, so nothing can be published or purchased. See examples/README.md for expected output.

Requirements

  • Node.js >= 20.
  • Network access to https://three.ws (or your own THREE_WS_BASE).

Environment variables

VariableRequiredDefault
THREE_WS_BASEnohttps://three.ws
THREE_WS_TIMEOUT_MSno20000

Links


Part of the three.ws SDK suite — 3D AI agents, on-chain identity, and agent payments.
Website · Changelog · GitHub

Source: packages/marketplace-mcp/README.md at commit c8f2cde

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

2
  1. v0.1.3LatestOct 10, 2026
  2. v0.1.2Sep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts