
Token Safety Check
io.github.lx1112Published by GitHub account lx1112v0.4.1Updated Oct 26, 2026
Rug check tokens on Base, Ethereum, Arbitrum, Optimism, Polygon, Solana: 0-100 risk score + reasons
The publisher's own server: check.tattoo: tattoo size and placement guide
Overview
Rug-check tokens on Base, Ethereum, Arbitrum, Optimism, Polygon or Solana: a 0-100 risk score with plain-language reasons, paid per call in USDC.
- What you can do
- Run a full safety check on one token: risk score, level and reasons, plus owner, authorities, supply, holders, pools, price and liquidity
- Get a chat-ready verdict with a grade, one-liner, short take and share-card link
- Re-check up to five tokens in one call and get one-line alerts on what changed since a stored fingerprint
- Compare against an earlier fingerprint to see new risks, authority changes, liquidity or price moves
- When to use it
- Useful when an assistant is asked whether a token is safe or should be bought, or when you want scheduled monitoring of a small set of tokens across the listed chains. It is a rules-based screen, not investment advice.
- Requirements
- Runs locally via npx (Node.js). Needs a dedicated wallet private key in X402_PRIVATE_KEY holding a little USDC on Base, since each check costs $0.01 via x402; no account or API key. Optional TOKEN_SAFETY_MAX_USD sets the per-call spending cap (default 0.05) and TOKEN_SAFETY_ENDPOINT points at another deployment. Network access to the payment endpoint is required.
Installation
In SourceWeft
- Open Token Safety Check in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
token-safety-check
Is this token safe? A rug check for any token on Base, Ethereum, Arbitrum, Optimism, Polygon or Solana, for AI agents and scripts. Each check returns:
- a 0–100 risk score and level (low, medium, high, critical) with plain-language reasons:
- who can mint, freeze, blacklist, pause or change fees
- upgradeable contract code
- Token-2022 permanent delegates, transfer fees and hooks
- holder concentration
- thin or missing liquidity
- a deployer whose earlier tokens lost their liquidity, or who launches tokens in bulk
- the facts behind the score: owner, authorities, supply, top holders, pools, and the deployer's launch record when we saw the token launch;
- USD price and liquidity;
- a fingerprint. Pass it back as
sinceand the next check tells you what changed: new risks, authority changes, liquidity or price moves. That makes it easy to monitor tokens on a schedule.
A verdict call turns the same facts into a grade (CLEAN, MID, SKETCHY or RUGGY), a one-liner, a short take and a link to a share card, for chat replies and quests.
A watchlist call re-checks up to 5 tokens at once for the same $0.01, returning a compact entry per token and one-line alerts for whatever changed since your last call.
Checks, verdicts and watchlist calls cost $0.01 each in USDC on Base, paid automatically with x402 from a wallet you control. There's no account or API key. Errors and invalid input are never charged, and a spending cap stops any call priced above your limit (default $0.05).
The score is rules-based and is not investment advice. Powers count for less on tokens with deep liquidity, where they're usually a large issuer's compliance controls (USDC can freeze and mint, for example).
Use it from Claude Desktop, Cursor or any MCP client
Create a new wallet just for this and send it a little USDC on Base: $1 covers 100 checks. Then
add to your MCP config (for Claude Desktop, that's claude_desktop_config.json):
The server has three tools:
check_token_safety(address, optionalchainandsince): the full check for one token.token_verdict(address, optionalchain): a grade, one-liner, short take and share-card link.watch_tokens(tokens: up to 5 of{ address, chain?, since? }): re-checks them all in one paid call and, given each token's earlier fingerprint, reports what changed with one-line alerts.
Optional environment variables:
TOKEN_SAFETY_MAX_USD: per-check spending cap, default0.05.TOKEN_SAFETY_ENDPOINT: point at another deployment.
Use it from code
A verdict for a chat reply
Watch what you hold
Use it in the Vercel AI SDK or Mastra
token-safety-check/ai gives three ready tools (checkTokenSafety, tokenVerdict, watchTokens),
plain { description, inputSchema, execute } objects that both take as tools:
Use it in ElizaOS
token-safety-check/eliza is an ElizaOS 1.x plugin with one action, CHECK_TOKEN_SAFETY. When a
message names a token address ("is 0x… on Base safe?", "rug check "), the agent replies with
the verdict and a share-card link.
Settings: TOKEN_SAFETY_PRIVATE_KEY (a dedicated wallet with a little USDC on Base; falls back to
X402_PRIVATE_KEY), optional TOKEN_SAFETY_MAX_USD (default 0.05) and TOKEN_SAFETY_ENDPOINT.
Use it in Coinbase AgentKit
Use it in LangChain (JS)
Example output (trimmed)
Without this package
Both are plain x402 endpoints, so any x402 client can call them directly:
GET https://onchaincheck.dev/token?chain=<chain>&address=<address>[&since=<fingerprint>] and
GET https://onchaincheck.dev/watchlist?tokens=<chain>:<address>,...[&since=<fp>,...].
It's also listed in the x402 Bazaar.
Safety notes
- Use a dedicated wallet with a small balance. The key never leaves your machine; it only signs USDC payments of the quoted price.
- Each check's price is read from the server's payment request before paying, and anything above
maxUsdPerCheck/TOKEN_SAFETY_MAX_USDis refused.
MIT licensed.
Source: README.md at commit a2e05c8
Tools
0Version history
5- v0.4.1LatestOct 26, 2026
- v0.4.0Oct 26, 2026
- v0.3.0Oct 25, 2026
- v0.2.0Oct 24, 2026
- v0.1.0Oct 23, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Other Check integrations
check.tattoo: tattoo size and placement guide
tattoo.checkOfficial publisher
check.tattoo: tattoo size and placement guide's hosted MCP server, published by check.tattoo; no sign-in required; Streamable HTTP; 5 tools.
iva.pt — EU VAT check (VIES) and Portuguese VAT law
pt.ivaOfficial publisher
Validates EU VAT numbers against VIES and returns Portuguese VAT Code (CIVA) and RITI articles, in Portuguese or English.

Dirtsmith Evidence Quote Check
Published by GitHub account throttler300
A local MCP server that binds an assistant's citations to admitted source text with spans and can reject stale-hash references.

HTTP Header Policy Check — HSTS, CSP & Frame Declarations
Published by GitHub account kriton-dev
Remote Apify-hosted MCP server that lets an assistant check seven declared HTTP security header families on a site, without returning raw header values.

VOOPA Render Check
Published by GitHub account Voopa-Corp
Reviews a completed AI-generated video against its brief and recommends whether to edit, retry once, or change approach before paying for another render.