Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Coin smart-money scores, wallet reputation, signal feeds, and KOL leaderboards.
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": {
"intel": {
"command": "npx",
"args": [
"-y",
"@three-ws/intel-mcp"
],
"env": {
"THREE_WS_BASE": "your-value",
"THREE_WS_TIMEOUT_MS": "your-value"
}
}
}
}Run this in your terminal
claude mcp add intel --env THREE_WS_BASE=your-value --env THREE_WS_TIMEOUT_MS=your-value -- npx -y @three-ws/intel-mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"intel": {
"command": "npx",
"args": [
"-y",
"@three-ws/intel-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": {
"intel": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@three-ws/intel-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 6, 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, Fomu MCP
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.
Kenya government form guides: checklists, draft letters, eCitizen, Huduma, timelines. Sample data.
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/intel-mcp
Read the market the way the smart money does — smart-money scoring, wallet intel, signal feeds, KOL trades, and the copy-trade directory, from any AI agent.
A Model Context Protocol server that gives any AI assistant the three.ws market-intelligence surface over stdio. Judge a coin by *who* is buying it, pull a wallet's realized reputation, read a signal feed's proven accuracy, rank KOL traders, and browse the copy-trade Smart Money directory — all live, read-only, no key required.
Every score, signal, and ranking comes straight from the public three.ws API. No API key, no signer, no payment — point THREE_WS_BASE at a deployment and go.
npm install @three-ws/intel-mcp
Or run with npx (no install):
npx @three-ws/intel-mcp
Claude Code, one line:
claude mcp add intel -- npx -y @three-ws/intel-mcp
Claude Desktop / Cursor (claude_desktop_config.json or mcp.json):
{
"mcpServers": { "intel": { "command": "npx", "args": ["-y", "@three-ws/intel-mcp"] } } }
Inspect the surface with the MCP Inspector:
npx -y @modelcontextprotocol/inspector npx @three-ws/intel-mcp
| Tool | Type | What it does |
|---|---|---|
smart_money_coin | read-only | Score a coin by WHO is net-buying it — 0–100 smart-money score, reputable buyers, funder clusters, sybil flag. |
wallet_intel | read-only | One wallet's realized reputation: score, win rate, behavioral labels, and its funder cluster. |
wallet_linkage | read-only | Cross-check 2-10 Solana wallets for shared control: 0-100 same-controller score per pair, with evidence. |
signal_feed | read-only | A signal feed's proven accuracy (hit-rate, realized/follower ROI) and recent emissions with on-chain proof. |
kol_leaderboard | read-only | Rank tracked KOL traders by realized P&L over a 7d / 30d window. |
kol_trades | read-only | Recent KOL trades on a specific mint, across the tracked KOL set. |
copy_smart_wallets | read-only | Browse the ranked copy-trade Smart Money directory — filter by chain, category, and sort. |
All seven tools read live data: scores, feeds, and rankings move between calls, so none are idempotent.
`smart_money_coin` — mint (required), network (mainnet | devnet, default mainnet).
`wallet_intel` — wallet (required), network (mainnet | devnet, default mainnet).
`wallet_linkage`: addresses (required, array of 2-10 Solana addresses).
`signal_feed` — slug (required), network (mainnet | devnet, default mainnet).
`kol_leaderboard` — window (7d | 30d, default 7d), limit (1–100, default 25).
`kol_trades` — mint (required), limit (1–100, default 20).
`copy_smart_wallets` — chain (sol | bsc), category (smart_money | launchpad | kol | sniper), sort (profit | pnl | winrate | followers | score, default score), q (text), limit (1–100, default 30), offset (default 0).
// copy_smart_wallets
{ "chain": "sol", "sort": "winrate", "limit": 3 }
{ "ok": true, "count": 3, "total": 412, "offset": 0, "limit": 3, "has_more": true, "facets": { "byChain": { "sol": 300, "bsc": 112 }, "byCategory": { "smart_money": 180, "kol": 90 } }, "wallets": [ { "address": "…", "chain": "sol", "categories": ["smart_money"], "score": 94, "win_rate_30d": 0.71, "realized_profit_30d_usd": 182000, "follow_count": 1240 } ] }
// smart_money_coin
{ "mint": "FeMbDoX7R1Psc4GEcvJdsbNbZA3bfztcyDCatJVJpump" }
{ "ok": true, "mint": "FeMbDoX7R1Psc4GEcvJdsbNbZA3bfztcyDCatJVJpump", "network": "mainnet", "computed": true, "smart_money_score": 78, "reputable_buyers": 12, "sybil_flag": false, "sybil_share": 0.18, "wallets": [ /* reputable buyers with realized_score, win_rate, labels */ ], "clusters": [ /* funder clusters in the book */ ] }
computed: false on a coin or wallet means the smart-money graph has no on-chain history for it yet — that's an honest "not enough data", not a failure.
// wallet_linkage
{ "addresses": ["FeMbDoX7R1Psc4GEcvJdsbNbZA3bfztcyDCatJVJpump", "11111111111111111111111111111111"] }
{ "ok": true, "addresses": ["FeMbDoX7R1Psc4GEcvJdsbNbZA3bfztcyDCatJVJpump", "11111111111111111111111111111111"], "pairs": [ { "a": "FeMbDoX7R1Psc4GEcvJdsbNbZA3bfztcyDCatJVJpump", "b": "11111111111111111111111111111111", "score": 0, "band": "none", "topSignal": null, "signals": [], "evidence": [] } ], "complete": true }
complete: false on the response means at least one address's history walk hit its time or request budget before finishing: scores are still real signals, just possibly based on partial history.
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