# VerdictSwarm

Fight AI with AI. The security layer for AI agents that touch money. 6 adversarial AI agents independently analyze, debate, and reach consensus on any token — catching what single-algorithm scanners …

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y @smithery/cli@latest mcp add sentien-labs/verdictswarm-mcp

# Browse available tools
npx -y @smithery/cli@latest tool list sentien-labs/verdictswarm-mcp

# Get full schema for a tool
npx -y @smithery/cli@latest tool get sentien-labs/verdictswarm-mcp scan_token

# Call a tool
npx -y @smithery/cli@latest tool call sentien-labs/verdictswarm-mcp scan_token '{}'
```

## Direct MCP Connection

Endpoint: `https://verdictswarm-mcp--sentien-labs.run.tools`

**Optional config:**
- `apiKey` (query) — Optional API key for higher rate limits. Leave empty for free tier (10 scans included).

## Tools (6)

- `scan_token`
- `get_quick_score`
- `check_rug_risk`
- `get_token_report`
- `get_pricing`
- `verify_payment`

```bash
# Get full input/output schema for a tool
npx -y @smithery/cli@latest tool get sentien-labs/verdictswarm-mcp <tool-name>
```

## Resources

- `verdictswarm://help`
- `verdictswarm://scoring`

## Prompts (2)

- `should_i_buy` (token_address, chain)
- `portfolio_check` (tokens, chain)