mcpField
G
GL1TCH Token Safety

GL1TCH Token Safety

Remote
gl1tchbased.xyzOther0Updated today

About GL1TCH Token Safety

GL1TCH Token Safety is a read-only scanner for token risks on Solana and 15 EVM chains. It serves token buyers and app builders with scored checks explained in plain language, without requesting wallet signatures.

Key features

  1. 010–100 token risk score
  2. 02Solana authority and liquidity checks
  3. 03EVM honeypot and tax checks
  4. 04Deployer history and linked-wallet signals
  5. 05Public scan API and Telegram alerts

Use cases

  1. 01Review a token before buying
  2. 02Check a deployer's record across launches
  3. 03Search tokens by name or symbol
  4. 04Build token checks into an app

MCP support

The project provides machine-readable documentation for agents, but the supplied README does not describe an MCP server or its exposed tools.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gl1tchbased.xyz/api/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

GL1TCH — scan before you buy

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.

Why it exists

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.

What every Solana scan checks

CheckWhat it catches
Mint authorityCan someone still print new supply?
Freeze authorityCan your wallet be frozen so you can't sell?
Transfer taxHidden Token-2022 transfer-fee extensions
LiquidityDepth, and fabricated depth (huge pool, no trades)
LP locked / burnedCan the dev pull the pool?
Top holder / insidersConcentration and bundled or insider wallets
DeployerThe launching wallet's track record across tokens
Deployer holdingsHow much of the supply the deployer holds right now (dump risk, or exited)
Trading activityBot volume: thousands of micro-trades, buy-bot skew, the same wallets trading back and forth
Linked walletsA holder count inflated by one network of wallets that fund each other
MetadataCan the name and image still be swapped?
RugCheckAn 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.

Use it from your own app (free, no key)

// Full safety report for one token
const r = await fetch("https://gl1tchbased.xyz/api/scan?mint=<address>&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 [email protected]; it stays free.

Embed a live badge that links to the full report:

<a href="https://gl1tchbased.xyz/scan/solana-<address>">
  <img src="https://gl1tchbased.xyz/api/badge?t=solana-<address>" alt="Scanned by GL1TCH" />
</a>

Machine-readable docs for agents: https://gl1tchbased.xyz/llms.txt.

How it's built

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]
PathWhat lives there
src/lib/scan.ts, src/lib/scan-multichain.tsThe 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)

Run it locally

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 and honesty

  • Read-only by design. The scanner and bot never request a transaction signature. See SECURITY.md to report a vulnerability, and docs/threat-model.md.
  • A verdict is a risk signal, not a guarantee, and never financial advice.
  • Verdict anchoring (live on mainnet since 25 Oct 2026): each Rug Radar sweep's verdicts are sealed on Solana as a Merkle root in one SPL Memo, so anyone can prove a verdict existed at that time, unedited. The memos are signed by a dedicated fee-only attester wallet, never a user's. Check one in your browser at https://gl1tchbased.xyz/verify-scan; the spec is docs/verdict-anchoring.md.
  • Public numbers come with their caveats: the scan counter's all-time total includes automated Rug Radar sweeps; since 20 Oct 2026 people's scans and automated ones are counted separately (/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 $GL1TCH token (disclosure)

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 locked.

  • Safety is never token-gated. The scanner, its API, the badge, Rug Radar and Watchtower are free for everyone. Holding the token only unlocks community ranks and the verifiable-randomness API.
  • Deployer wallet: sold its full position on 2026-08-20, then bought back about 3.1% of supply on 17–19 Oct 2026. The live balance and both receipts are on the Proof page.
  • The market is very thin. Grant funding is never used for the token, buybacks or liquidity.

More: whitepaper · token page · Quantum Core and verifiable randomness.

Contributing

Issues and pull requests are welcome. See CONTRIBUTING.md.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.