VerdictSwarm

Fight AI with AI. 6 adversarial AI agents debate crypto token risk before your agent trades. Rug-pull detection, security audits, consensus scoring via MCP.

Security Scan

The skill's declared purpose (multi-agent token risk scanning) matches its instructions and resource requests; it only requires network access to api.vswarm.io and gives expected CLI/API usage, so its footprint is internally coherent.

Purpose & Capability

Name/description (multi-agent token analysis) align with the SKILL.md: it instructs calls to https://api.vswarm.io and describes MCP helpers for scanning, scoring, and reports. No unrelated credentials, binaries, or config paths are requested.

Instruction Scope

Runtime instructions are narrowly scoped: use MCP tools or call the vendor API, present score/consensus, and include report URL. The skill does not ask the agent to read local files, access unrelated env vars, or transmit data to unexpected endpoints beyond api.vswarm.io.

Install Mechanism

The SKILL.md recommends a pip package (verdictswarm-mcp) but provides no install spec; that is expected for an instruction-only skill. Installing third-party Python packages can execute arbitrary code — users should review the package/source (e.g., PyPI listing or upstream repository) before running pip install.

Credentials

No environment variables, credentials, or config paths are required. The suggested operations (API calls and optional pip package) do not demand secrets from the user. Payment operations referenced (USDC on Solana) imply on-chain tx verification but do not request private keys.

Persistence & Privilege

This is an instruction-only skill with no install spec that would write persistent artifacts. always is false and there is no request to modify system or other skills' configurations.

Assessment

This skill appears coherent with its stated purpose, but take ordinary precautions: 1) Confirm the vendor domain (api.vswarm.io) is legitimate before sending token addresses or payment info. 2) Never share private keys or wallet seed phrases; the API should only receive public addresses/tx hashes. 3) If you plan to pip install verdictswarm-mcp, inspect the package source (PyPI page or upstream Git repo) to ensure it is trustworthy. 4) Be aware of pay-per-scan costs (USDC on Solana) and verify any on-chain payment flows independently. If you need higher assurance, ask the publisher for a homepage, source repository, or signed release artifacts before use.

VerdictSwarm — Multi-Agent Token Intelligence

Get a second, third, fourth, fifth, and sixth opinion on any crypto token.

Six specialized AI agents independently analyze your token from different angles, then debate their findings across multiple rounds before reaching consensus. You see the full analysis and any disagreements.

"What do you think of this token?" → 6 agents analyze → Consensus reached → You decide

Free tier available. 10 quick scans per day, no API key needed.

How It Works

Each agent specializes in a different aspect of token analysis:

Agent	Focus Area
Security Bot	Smart contract permissions, mint/freeze authority, honeypot detection
Tokenomics Bot	Supply mechanics, holder concentration, distribution
Social Bot	Community signals, social presence, engagement patterns
Technical Bot	On-chain metrics, liquidity analysis, trading patterns
Macro Bot	Market context, comparative analysis, sector trends
Devil's Advocate	Challenges every verdict, finds what others missed

MCP Tools

Install via MCP for agent integration:

pip install verdictswarm-mcp

Tool	Description
scan_token	Full 6-agent consensus risk scan
get_quick_score	Fast cached score (0-100) for pre-trade screening
check_rug_risk	Rug-pull focused security check (SAFE/CAUTION/DANGER)
get_token_report	Shareable markdown report
get_pricing	View pricing and Solana payment details
verify_payment	Verify USDC payment on Solana

Quick Start (API)

curl -s "https://api.vswarm.io/api/scan/quick" \
  -H "Content-Type: application/json" \
  -d '{"address": "JUPyiwrYJFskUPiHa7hkeR8VUtAeFoSYbKedZNsDvCN", "chain": "solana"}'

Scoring Guide

• 80-100: LOW risk (Grade A)
• 70-79: LOW-MEDIUM (Grade B)
• 60-69: MEDIUM (Grade C)
• 40-59: HIGH (Grade D)
• 0-39: CRITICAL (Grade F)

Pricing

Tier	Cost	Details
Free	$0	10 quick scans/day
Quick Scan	0.02 USDC	Cached score + metadata
Rug Check	0.05 USDC	Security-focused verdict
Full Scan	0.10 USDC	All 6 agents, full debate

Pay per scan with USDC on Solana, or use a free API key from vswarm.io.

Supported Chains

Solana, Ethereum, Base, BSC

Agent Instructions

When the user asks to analyze or check a crypto token, use the MCP tools (preferred) or call the API directly. Present the verdict score, risk level, and consensus summary. If agents disagreed, highlight the differences. Include the report URL for the full breakdown.