Wicked MCP
io.github.WickedAPI/wicked-mcp · v1.6.5 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Whole Wicked suite for agents: market data, SEC filings, wallet checks, risk, identity, memory.
Source: https://github.com/WickedAPI/wicked-mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 108 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 2 tool(s) can execute commands or delete data (memory_delete, paywall_delete_route). Require confirmation before the agent calls them. |
What was checked
- https://mcp.wickedapi.com/mcp: answers without auth
- npm: @wickedlabs/wicked-mcp@0.7.5 (static checks only; code not executed)
Public tools: kalshi_probability, kalshi_market, funding_oi, long_short_ratio, orderbook, basis, hyperliquid, volatility, sentiment, defi_tvl, price, ohlcv, atr, rates, market_clock, market_overview, gas, fvg, liquidity_levels, macro_calendar, earnings_calendar, wallet_portfolio, verdict, momentum_score, chain_balance, chain_token_balance, chain_nonce, chain_block, chain_ens, chain_tx
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-wickedapi-wicked-mcp-f9b2f46e)