Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Read the three.ws vanity-address market: quote difficulty + USDC price, browse the board.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
THREE_WS_BASE, THREE_WS_TIMEOUT_MSYou need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"vanity": {
"command": "npx",
"args": [
"-y",
"@three-ws/vanity-mcp"
],
"env": {
"THREE_WS_BASE": "your-value",
"THREE_WS_TIMEOUT_MS": "your-value"
}
}
}
}Run this in your terminal
claude mcp add vanity --env THREE_WS_BASE=your-value --env THREE_WS_TIMEOUT_MS=your-value -- npx -y @three-ws/vanity-mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"vanity": {
"command": "npx",
"args": [
"-y",
"@three-ws/vanity-mcp"
],
"env": {
"THREE_WS_BASE": "your-value",
"THREE_WS_TIMEOUT_MS": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"vanity": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@three-ws/vanity-mcp"
],
"env": {
"THREE_WS_BASE": "your-value",
"THREE_WS_TIMEOUT_MS": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
THREE_WS_BASE envTHREE_WS_TIMEOUT_MS envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account nirholas, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.1.3) reached the registry 27 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Spec Driven Development, Remote Desktop Commander, TF Rooms
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Live room availability, rates and stay quotes for 12 New Leaf motels in Twin Falls, Idaho.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
@three-ws/vanity-mcp
Read the three.ws vanity-address grind-bounty market + rarity gallery from any AI agent.
A Model Context Protocol server that gives any AI assistant the read/discovery surface of the three.ws vanity-address grind-bounty market over stdio. Quote how hard a Solana vanity pattern is and what to escrow for it, appraise the rarity of any address, and browse the live bounty board, claimable queue, stats, leaderboard, config, and the proof-of-grind gallery.
The market is secret-blind: a requester escrows a USDC bounty for a pattern, a fleet of independent workers grinds it in parallel, and the first to submit a verified key matching the pattern is paid on-chain — yet the found secret is sealed to the requester, so the worker earns the bounty without ever seeing the wallet. Posting a bounty and claiming one are the x402-paid write paths on the HTTP API; this MCP exposes the read/discovery + rarity surface. No API key, no signer, no payment — every call hits the public /api/vanity endpoints.
npm install @three-ws/vanity-mcp
Or run with npx (no install):
npx @three-ws/vanity-mcp
Claude Code, one line:
claude mcp add vanity -- npx -y @three-ws/vanity-mcp
Claude Desktop / Cursor (claude_desktop_config.json or mcp.json):
{
"mcpServers": { "vanity": { "command": "npx", "args": ["-y", "@three-ws/vanity-mcp"] } } }
Inspect the surface with the MCP Inspector:
npx -y @modelcontextprotocol/inspector npx @three-ws/vanity-mcp
| Tool | Type | What it does |
|---|---|---|
vanity_quote | read-only | Price a pattern: expected attempts, rarity tier, and an honest suggested USDC bounty. Idempotent. |
vanity_appraise | read-only | Appraise any Solana address's rarity (pattern, score, bits, tier, attempts). Idempotent. |
vanity_board | read-only | Browse the grind-bounty board — filter by status, sort by recency/reward/expiry, paginate. |
vanity_open | read-only | List the claimable open-bounty queue workers poll. |
vanity_stats | read-only | Live market totals: open count, USDC escrowed, USDC paid out. |
vanity_leaderboard | read-only | Top grinders ranked by total USDC earned. |
vanity_config | read-only | Payout availability + asset/network metadata (settlement asset, decimals, networks, pricing band). |
vanity_gallery | read-only | Browse the proof-of-grind rarity gallery — sort, filter by tier/length/substring, paginate. |
vanity_quote and vanity_appraise are pure functions of their input (same pattern/address → same result), so they're marked idempotent. The other six read the live market and gallery.
`vanity_quote` — prefix (optional Base58 prefix), suffix (optional Base58 suffix), ignoreCase (bool, default false). At least one of prefix/suffix is required.
`vanity_appraise` — address (required, Base58 32–44 chars), prefixLen (int, optional), suffixLen (int, optional).
`vanity_board` — status (open | all | settled, default open), sort (recency | reward | expiry, default recency), limit (1–100, default 24), offset (default 0).
`vanity_open` — limit (1–100, default 30).
`vanity_stats` — no params.
`vanity_leaderboard` — limit (1–100, default 10).
`vanity_config` — no params.
`vanity_gallery` — sort (score | recency, default score), tier (string), minLength (int), contains (string), limit (1–100, default 24), offset (default 0).
// vanity_quote
{ "prefix": "THREE" }
{ "ok": true, "pattern": { "prefix": "THREE", "suffix": null, "ignoreCase": false }, "difficulty": { "expectedAttempts": 11308763834, "rarityBits": 39, "tier": "mythic", "tierLabel": "Mythic", "accent": "#ff5db1", "expectedGrindSeconds": 7539 }, "oracle": { "floorAtomics": 50000, "suggestedAtomics": 2094216, "generousAtomics": 5235540, "maxAtomics": 5000000000, "expectedAttempts": 11308763834, "expectedGrindSeconds": 7539, "model": "58^effectiveLength @ refRate" }, "band": { "floorAtomics": 50000, "maxAtomics": 5000000000, "decimals": 6, "asset": "USDC" } }
Runnable examples live in examples/:
node examples/list-tools.mjs # every tool with its full input schema
node examples/quote-and-appraise.mjs # config + quote + appraise + stats, live
Both spawn this server over stdio and read the live market. Every tool here is read-only, so nothing can be posted, claimed, or paid. See examples/README.md for expected output.
https://three.ws (or your own THREE_WS_BASE).| Variable | Required | Default |
|---|---|---|
THREE_WS_BASE | no | https://three.ws |
THREE_WS_TIMEOUT_MS | no | 20000 |
Part of the three.ws SDK suite — 3D AI agents, on-chain identity, and agent payments.
Website · Changelog · GitHub