Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Description from the maker (original English)
Token rug-risk scans, Know Your Agent wallet checks and deployer reputation for AI agents.
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.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://gl1tchbased.xyz/api/mcpRun this in your terminal
claude mcp add --transport http gl1tch https://gl1tchbased.xyz/api/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"gl1tch": {
"url": "https://gl1tchbased.xyz/api/mcp"
}
}
}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": {
"gl1tch": {
"type": "http",
"url": "https://gl1tchbased.xyz/api/mcp"
}
}
}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.
ChatGPT connects only to servers on the internet:
https://gl1tchbased.xyz/api/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
We have not read this server’s tool list yet; we check endpoints in rotation.
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 gl1tchbased-pixel, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
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 in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.0.0) reached the registry 9 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Spec Driven Development, Remote Desktop Commander, dotnet-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.
MCP server for .NET symbols, XAML, source generators, and restricted workspace edit
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.
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.