HyperSignal MCP
io.github.johnsmithxy1mmm-sys/hypersignal-mcp · v1.14.0 · 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
Hyperliquid analytics for AI agents: whale flow, liquidations, funding, risk, signed signals.
Source: https://github.com/johnsmithxy1mmm-sys/HyperliquidMCP
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 30 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 2 tool(s) can execute commands or delete data (hl_delete_webhook, hl_delete_alert). Require confirmation before the agent calls them. |
What was checked
- https://hypersmash.fly.dev/mcp: answers without auth
- npm: hypersignal-mcp@1.14.0 (static checks only; code not executed)
Public tools: hl_request_free_key, hl_buy_pro, hl_get_markets, hl_get_orderbook, hl_get_candles, hl_get_funding_history, hl_get_account, hl_get_open_orders, hl_signal_pubkey, hl_link_telegram, hl_unlink_telegram, hl_set_webhook, hl_delete_webhook, hl_score_calibration, hl_whale_positions, hl_whale_flow_alerts, hl_liquidation_map, hl_funding_screener, hl_hip3_analytics, hl_portfolio_risk, hl_vault_screener, hl_trader_report, hl_create_alert, hl_list_alerts, hl_delete_alert, hl_poll_alerts, hl_signal_track_record, hl_smart_money_score, hl_coordination_scan, hl_polymarket_divergence
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-johnsmithxy1mmm-sys-hypersignal-mcp-18f04841)