Skip to main content
The failure mode this prevents: an agent looks up a token’s price, finds a number, and reports that it is worth something. The contract turns out to be a honeypot you can buy but never sell. Two tools cover this job. check_token_safety is the quick screen for one contract. research_token is the full report: identity, market, liquidity, holders and safety in one call.

Quick screen

Check whether the token at 0x6B175474E89094C44Da98b954EedeAC495271d0F on Ethereum is safe to interact with. Show the risk signals and cite your sources.
Your agent calls check_token_safety:
It returns GoPlus risk_flags (honeypot, buy and sell tax, mintable, hidden owner and more), a summary with LP lock status, top-holder concentration and plain-language verdicts, and a source_receipt. It costs 1 credit. Solana mints are detected from the address.

Full due diligence

Research PEPE on Ethereum: is it liquid, how concentrated are the holders, and is the contract safe? Cite each source.
Your agent calls research_token:
1

Resolve the asset

The name is resolved first. If several tokens share it, the call stops with AMBIGUOUS_TOKEN and lists the candidates, and you are not charged. Pick one by id, or pass the contract and chain. An agent that skips this step will happily analyze the wrong contract.
2

Market

Price, market cap, FDV, 24h volume, and 7d and 30d change.
3

Liquidity

The top DEX pools with reserve and volume. A clean contract with two thousand dollars of liquidity is still untradeable at size.
4

Holders

The top holders. If a handful of wallets hold most of the supply, a clean scan does not mean much.
5

Safety

The same GoPlus screen check_token_safety runs.
That costs 5 credits. Add "sections": [..., "top_traders"] to see who has been trading it, for 1 more credit. When you only have a name and want to confirm the contract first, call find_token (1 credit).

Reading the answer

Three questions decide whether the result is usable:
  • Which provider ran each section. Each section has its own source. Coverage differs by chain, and a risk score for a chain the provider barely indexes is weak evidence.
  • How old the data is. Contract ownership can change. A scan from an hour ago is not a statement about now.
  • What is under missing. A section that failed is listed there rather than guessed. A degraded security provider is the one case where you should re-run rather than trust the answer.

What a clean result does not tell you

A contract that passes every automated check can still be a rug. These signals catch mechanical traps, not intent. Treat a clean scan as the absence of known red flags, not proof of safety, and size positions accordingly.