Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Coin smart-money scores, wallet reputation, signal feeds, and KOL leaderboards.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
THREE_WS_BASE, THREE_WS_TIMEOUT_MS你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 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"
}
}
}
}在终端中运行这条命令
claude mcp add intel --env THREE_WS_BASE=your-value --env THREE_WS_TIMEOUT_MS=your-value -- npx -y @three-ws/intel-mcp运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.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"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"intel": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@three-ws/intel-mcp"
],
"env": {
"THREE_WS_BASE": "your-value",
"THREE_WS_TIMEOUT_MS": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
THREE_WS_BASE envTHREE_WS_TIMEOUT_MS env这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日
注册名称已通过 GitHub 账户 nirholas 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.1.3)于27天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
同一分类中有:Spec Driven Development, Remote Desktop Commander, yontu
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
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.
Türkçe yazı denetimi: TDK kuralları, yapay zekâ izleri, metin türüne göre üslup.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
@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