// PRE-TRADE RISK GATE

The trust layer before an agent or person buys a token.

Call the API or paste a contract before money moves. VerdictSwarm returns avoid, caution, or clear from 6 risk analysts, with the signals and report URL needed to verify the call.

Live on Virtuals ProtocolSupports Solana · Base
Swarm terminalSample — recorded

$ pre-trade check JUPyiw…DvCN solana

[FreeTierAI] score 8.2 · bullish

[honeypot_simulation] Sell simulation passed.

[mint_authority] Mint authority revoked — cannot inflate supply.

[freeze_authority] Freeze authority revoked — holders cannot be frozen.

[top10_holder_concentration] Top-10 wallets hold 66.2% of supply.

$ decision: caution · score 82 · grade A

Two panels. Without VerdictSwarm: six sources — contract, holders, liquidity, socials, wallets, market — tangled by dashed lines into question marks, a chaos meter pegged at the red end, terminating in INDECISION. With VerdictSwarm: the same meter reading NONE in green, and one straight line — contract to VerdictSwarm to a verdict — captioned ONE CALL. ONE DECISION.

TRY IT / NO SIGNUP

Inspect the output before you wire it up.

Scan level

300 fast + 10 deep scans/day · midnight UTC reset

One-click demos

No signup for the web demo.

What happens next

  1. 01Paste a tokenUse a Solana mint, Base contract, or one-click example.
  2. 02Get avoid, caution, or clearScore, grade, and the signals that drove the call.
  3. 03Use the report as proofA shareable URL you can send to anyone who asks.

Total observations

Avoid calls

Documented misses

Trending right now

DexScreener · refreshes every 5 min

TokenChainPrice24hLiquidity

Trending data unavailable right now.

One risk gate before the agent acts.

How it works

01

Agent proposes

A bot, wallet, dashboard, or ACP buyer has a token it wants to buy, list, alert, or route.

02

Call verdict

Send address, chain, and level to POST /v2/verdict, MCP, or the ACP service.

03

Read decision

Receive avoid, caution, or clear with score, top signals, and billing metadata.

04

Act on verdict

Gate execution, enrich the alert, or open the report URL when a human needs details.

Why this matters

Agents move faster than humans can inspect.

Trading agents, launch tools, wallets, and alert bots need a repeatable stop/go signal before automation turns a weak token into a real loss.

Live on-chain data

Contract state, liquidity depth, and holder distribution read at verdict time.

Decision first

The API returns an action your system can branch on before it reads a report.

Machine-payable

Prepaid credits or x402 USDC micropayments for machine buyers.

Repeatable

Cache-aware pricing lets agents re-check tokens without paying full fresh-scan cost.

Verified catches

$CRABGE

23/100 · Avoid

$CRABGE scored 23/100 — flagged for active mint authority, extreme vol/liq ratio, and 83% holder concentration. Price crashed 83% within 24 hours.

$ASH20

39/100 · Avoid

$ASH20 scored 39/100 — flagged for suspicious deployer history and concentrated holdings. Delisted within 48 hours. $30k liquidity gone.

Open proof receipts →

Live on Virtuals Protocol

Address in. Structured verdict plus report URL out.

VerdictSwarm is available as an ACP-native agent service. Trading agents can request a pre-trade risk check before they buy, alert, list, or recommend a contract.

Integrate via ACP

ACP job

job
preTradeTokenRiskCheck
agent
VerdictSwarm
input
address + chain
output
decision, score, top signals, reason, report URL
price
$0.05 per check

See the output

Decision first. Reading material second.

Your system branches on one field. The long report exists for the moment a human has to justify the call.

  • Live contract state read at verdict time
  • Credits or x402 USDC micropayments
  • Cache-aware pricing for repeat checks
  • Shareable report URL as a proof receipt
Sample — recorded verdict$CRABGE · Solana
AVOID

23/100

Grade F

  • Mint authority: Active — can mint unlimited tokens
  • Vol/Liq ratio: 47:1 — wash trading signal
  • Top 10 holders control 83% of supply
  • Token age: <48 hours

Verdict: This token fails a pre-trade risk check and should be avoided.

View full report →

API for agents. Web scan when a human wants to look.

Use it where you operate

API / ACP / MCP

Agent lane
  • Call before execution
  • Decision + score + top risks
  • Credits or x402 payment rails
  • Report URL for human review

Web scanner

Your lane
  • Paste a token manually
  • Watch the same signal pipeline
  • Shareable report URL
  • Deeper reasoning when needed

Check it yourself before the money moves.

Access paths

// LAST STOP BEFORE YOU BUY

Run the check before you send it.

One call. One decision.