Skip to main content
Glama

dApp & Link Check (Crypto)

crypto_dapp_check
Read-onlyIdempotent

Open a crypto page — a dApp, airdrop, claim or mint link — and report what it asks a wallet to do. DechoNet opens it in an isolated Chromium (Seoul) with a test wallet that holds nothing (EVM, Solana and TRON): it presses the page's…

Instructions

Open a crypto page — a dApp, airdrop, claim or mint link — and report what it asks a wallet to do. DechoNet opens it in an isolated Chromium (Seoul) with a test wallet that holds nothing (EVM, Solana and TRON): it presses the page's "Connect wallet" button once (or one "Claim" button when there is none) and the test wallet in a wallet picker once; it types nothing and submits no form, and the test wallet connects with a burn address and refuses every signature and transaction. Reported: each wallet request in order with what approving it would allow (unlimited token approvals, setApprovalForAll, Permit/Permit2 signatures, transfers, Solana transactions, TRON approvals and account-permission changes), drainer-kit code markers in the page scripts, a connect button that sends the visitor to another site, and the phishing link check verdict of the same link (including whether it is the brand's own domain). Verdicts: danger, suspicious, official, no_signals, unreachable. no_signals means none of these were seen and is not a statement that the page is harmless: drainers that wait for a second press, show nothing to an automated browser or ask only after a sign-in can go unseen, and on new drainer samples few were caught by wallet requests alone (figures on dechonet.com/methodology); 'unchecked' lists what was not looked at. Every call opens the page (no cached answer), so it takes longer than the other checks, and it has a per-minute rate limit and a daily limit shared by all callers. Only the host, the verdict and the kinds of request are kept (90 days); no API key.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "url": "<url>"
    },
    "name": "crypto_dapp_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesAddress of the page to open (https://…; a bare domain is opened over https)

Output Schema

NameRequiredDescriptionDefault
hostNoThe host the page ended on
signalsYes
verdictYesno_signals: none of the checks saw a warning sign — not a statement that the page is harmless (see unchecked)
receiptsNoSigned observation receipts behind this result, one per lookup: when, from where and under which rules version DechoNet observed it. Each url shows the record and checks its Ed25519 signature.
renderedYesFalse when the page could not be opened with the test wallet (then little was seen)
requestsYesWallet requests the page made, in order
uncheckedYes
phishingVerdictNoThe phishing link check verdict for the same link

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.9.0

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds substantial behavior beyond the annotations: isolated Chromium in Seoul, a burn-address test wallet across EVM/Solana/TRON, exactly one connect (or one claim) press, no typing or form submission, refusal of all signatures, and the full set of reported signals. It also discloses the verdict vocabulary, the meaning and limits of no_signals, an unchecked list, per-call page opening, rate/daily limits, 90-day retention of host/verdict only, and that no API key is needed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core action is front-loaded and nearly every clause carries operational information, including the caveats that prevent over-trusting no_signals. It is a single very dense paragraph though, and the methodology URL plus the enumeration of request types make it heavier than needed for scanability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool that drives a browser and interacts with a page, the definition covers mechanism, safety posture, expected duration, limits, retention, and the exact verdict set, and an output schema exists so return formatting need not be spelled out. Nothing an agent needs to decide whether and how to call it appears to be missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is only one parameter and the schema already documents it at 100% coverage ('https://…; a bare domain is opened over https'). The description confirms the page is opened rather than fetched from cache, but adds no format or syntax detail about the url argument itself, so it sits at the expected baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence states a specific verb and resource — open a crypto page (dApp, airdrop, claim, mint link) and report what it asks a wallet to do — which is far more precise than the tool name alone. It also situates itself against the phishing link check by noting that verdict is folded in, so an agent can see it is the deeper option.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is clear: this is a pre-interaction check on a wallet-facing page, and the description explicitly notes it is slower than the other checks and subject to shared rate/daily limits, which signals when to prefer a lighter check. It never explicitly names a sibling to use instead when only a URL reputation verdict is needed, so it stops short of full when/when-not routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.