dappgrade
auregimon/dappgradePre-transaction health and safety verdicts for onchain apps, by contract address. Before an agent transacts with a dApp, ask what dappgrade observed: **ok** / **caution** / **avoid** / **unknown** — each carrying the *coverage* it rests on, so a partial result is never mistaken for a clean bill of health. `unknown` is a real, free answer: never infer safety from the absence of a rating. **Tools** - `get_score` — verdict for a (chain, address), with score, coverage, tier, flags and per-dimension sub-scores. Paid: 0.01 USDC via x402 on Base. Chain accepts an id (`8453`), CAIP-2 (`eip155:8453`), or a name (`base`). - `get_universe` — every dApp covered, with current scores and coverage. Free. - `get_methodology` — the rubric: tiers, three-state checks (pass / fail / not_reached), and the verdict model. Free. Addresses resolve through frontend→contract mappings harvested by driving real dApps through real wallet flows. Where an address is shared across apps (routers, Permit2), every candidate is returned rather than a silent pick.
Score: 100/100
Handshake verified by our own probe.
Tools · 3
Pre-transaction health/safety verdict for an onchain app, by contract address. Returns a decision-shaped verdict — ok / caution / avoid / unknown — with score, coverage, tier, flags and per-dimension …
List the dApps dappgrade covers, with current scores and coverage (free discovery manifest).
How dappgrade scores dApps: tiers 0/1/2, three-state checks (pass/fail/not_reached), coverage, and the verdict model. Free.
How to use
Claude Desktop or claude.ai: add a custom connector (Customize → Connectors; on Team and Enterprise plans an owner adds it under Organization settings → Connectors) with this server URL: https://dappgrade.vercel.app/api/mcp
Cursor or Cline: add to your MCP config:
{
"mcpServers": {
"dappgrade": {
"url": "https://dappgrade.vercel.app/api/mcp",
"transport": "http"
}
}
}