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)
Token rug-risk scans, Know Your Agent wallet checks and deployer reputation for AI agents.
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。
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 …”。
适用于网页版、桌面版和手机版 Claude:
https://gl1tchbased.xyz/api/mcp在终端中运行这条命令
claude mcp add --transport http gl1tch https://gl1tchbased.xyz/api/mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"gl1tch": {
"url": "https://gl1tchbased.xyz/api/mcp"
}
}
}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": {
"gl1tch": {
"type": "http",
"url": "https://gl1tchbased.xyz/api/mcp"
}
}
}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。
ChatGPT 只能连接互联网上的服务器:
https://gl1tchbased.xyz/api/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
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。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
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 gl1tchbased-pixel 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
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
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。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于–,最新版本(1.0.0)于9天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Symantec Cloud DLP AIops
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.
Governed Symantec Cloud DLP — 14 MCP tools, read-only with audit.
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。
A free, open-source token safety scanner for Solana (plus 15 EVM chains). Paste any token and get a 0–100 risk score with a plain-language reason for every check, in seconds. Read-only: it never asks for a signature, never touches a wallet, and costs nothing to use.
mobile/Most tokens launched on Pump.fun collapse shortly after launch (Solidus Labs counted 98.6% of 7M+ tokens from Jan 2024 to Mar 2025 as pump-and-dumps). The warning signs sit in on-chain state that buyers can't read: a live mint authority, a freeze authority, a hidden Token-2022 transfer fee, unlocked liquidity, bundled sniper wallets, a deployer with a history of rugs. GL1TCH reads that state, explains it in plain words, and gives it away for free.
| Check | What it catches |
|---|---|
| Mint authority | Can someone still print new supply? |
| Freeze authority | Can your wallet be frozen so you can't sell? |
| Transfer tax | Hidden Token-2022 transfer-fee extensions |
| Liquidity | Depth, and fabricated depth (huge pool, no trades) |
| LP locked / burned | Can the dev pull the pool? |
| Top holder / insiders | Concentration and bundled or insider wallets |
| Deployer | The launching wallet's track record across tokens |
| Deployer holdings | How much of the supply the deployer holds right now (dump risk, or exited) |
| Trading activity | Bot volume: thousands of micro-trades, buy-bot skew, the same wallets trading back and forth |
| Linked wallets | A holder count inflated by one network of wallets that fund each other |
| Metadata | Can the name and image still be swapped? |
| RugCheck | An independent second opinion |
A token whose volume is botted, or whose holders are mostly one linked network, can't read better than CAUTION, whatever its contract looks like. The scan also flags a token that has fallen 85% or more from its peak, and paid DexScreener promotion. EVM chains use GoPlus for honeypot, sell tax, mintable, ownership, pausable and blacklist checks, plus the same trading-activity check. Every scan also feeds the Signal Graph, a cross-scan memory of deployers, so a serial rugger's next token is flagged. Scoring changes are logged in docs/scoring-changelog.md.
// Full safety report for one token
const r = await fetch("https://gl1tchbased.xyz/api/scan?mint= &chain=solana"); const report = await r.json(); // { verdict, score, confidence, checks[], meta, bottomLine, ... }
// Search by name or symbol across chains const s = await fetch("https://gl1tchbased.xyz/api/scan?q=bonk").then((x) => x.json()); // { candidates }
Verdicts: CLEAN, LOW RISK, CAUTION, HIGH RISK, RUG-SHAPED, UNKNOWN. The API is rate limited per IP (40 requests/min), the same for every caller. If you are building an integration that needs more, ask at founder@gl1tchbased.xyz; it stays free.
Embed a live badge that links to the full report:
<a href="https://gl1tchbased.xyz/scan/solana-<address>">
" alt="Scanned by GL1TCH" />
Machine-readable docs for agents: https://gl1tchbased.xyz/llms.txt.
flowchart LR
U[Browser · Telegram · API caller] --> S["/api/scan (Next.js on Vercel)"] S --> RPC[Solana RPC: mint, authorities, holders, deployer balance] S --> RC[RugCheck: LP lock, insiders, deployer] S --> MK[DexScreener / GeckoTerminal: market] S --> GP[GoPlus: EVM checks] S --> BOT[(Bot on an Oracle Cloud VM: Signal Graph, counters, Watchtower)] BOT --> TG[Telegram alerts]
| Path | What lives there |
|---|---|
src/lib/scan.ts, src/lib/scan-multichain.ts | The scan engine: checks, weights, verdicts |
src/app/api/ | Public API routes (scan, badge, radar, stats, agent check) |
src/app/ | The website (Next.js App Router) |
bot/ | Telegram bot, Watchtower sweeps, Signal Graph and counters, stored as files on its VM (no database); hosting in bot/deploy/oracle |
mobile/ | Android prototype (Expo / React Native): share-to-scan, read-only wallet scan over Mobile Wallet Adapter, Sign in with Solana (demo video) |
docs/ | Threat model, risk register, scoring changelog, Signal Graph schema, specs |
remotion/, e2e/ | Video pipeline and browser automation (not needed to run the scanner) |
A working mobile-first Android prototype (mobile/, MIT) built for Solana Seeker and Android devices:
mobile/README.md.Requires Node.js 22.
npm install
cp .env.example .env.local # optional: a private Solana RPC in SCAN_RPC; public RPCs work for light use npm run dev # http://localhost:3000/scan npm test # unit tests (vitest)
cd bot && npm install && npm test # the Telegram bot has its own package and tests
CI type-checks and tests the site and the bot on every push, and a security workflow runs a secret scan, a dependency audit and a check that no code ever requests a fund-moving or approval signature.
SECURITY.md to report a vulnerability, and docs/threat-model.md.docs/verdict-anchoring.md./api/stats returns user, auto and splitSince, or a 503 while the counter is unreachable, never a made-up 0). Automated means Rug Radar, Watchtower, link previews, badge renders and our own pages' self-checks of $GL1TCH. Those self-checks were at first miscounted as people's scans, so the split restarted once that was fixed (splitSince is the restart).The project also has a community token, $GL1TCH (3HQJwwHvzy8pGkPqGQcb4thZCH88MUCHVVSNtHn6pump), launched on Pump.fun on 29 May 2026: Token-2022, mint and freeze authority revoked, 0% tax, fixed 1B supply, liquidity in the Pump.fun bonding curve.
More: whitepaper · token page · Quantum Core and verifiable randomness.
Issues and pull requests are welcome. See CONTRIBUTING.md.