hypernatt-terminal MCP Server

io.github.DIALLOUBE-RESEARCH/hypernatt-terminal

answering

hypernatt-terminal is answering right now. Last checked 10 min ago. It exposes 15 tools. Last commit 27 Jul 2026.

BTC/USDC decision context for AI agents from a live Hyperliquid vault; $0.001/call via x402.

Uptime history 41 hours of history · worst hour 43%

41 hours agonow

50.0%

Uptime 24h

91 of 182 checks

Tools

read from the server

174 ms

Response time

average over 24h

Stars

last commit 27 Jul 2026

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 10 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add hypernatt-terminal --transport http https://hypernatt.com/mcp/protocol

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "hypernatt-terminal": {
      "url": "https://hypernatt.com/mcp/protocol"
    }
  }
}

~/.codex/config.toml

[mcp_servers.hypernatt-terminal]
url = "https://hypernatt.com/mcp/protocol"

.cursor/mcp.json

{
  "mcpServers": {
    "hypernatt-terminal": {
      "url": "https://hypernatt.com/mcp/protocol"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "hypernatt-terminal": {
      "url": "https://hypernatt.com/mcp/protocol"
    }
  }
}

Available tools 15

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

swap

swap_quote

Raw Li.Fi swap quote JSON without execution steps. USE WHEN: preview route, fees, and slippage before swap_via_nattswap. NOT WHEN: you need step-by-step agent instructions (use swap_via_nattswap). RETURNS: Li.Fi quote { estimate, toolDetails, transactionRequest, ... }. Free — no x402. Side effects: none.

swap_via_nattswap

Cross-chain token swap powered by Li.Fi across 70+ chains incl. Hyperliquid (any pair — not limited to BTC/USDC). USE WHEN: bridge, fund gas, treasury routing, or rebalance after Decision Core. NOT WHEN: Decision Core BTC reads alone (get_btc_usdc_signal / trap / hunt) — vault signals stay BTC/USDC only. RETURNS: Li.Fi route + execution_readiness + swap_actions_v1 (ordered approve→swap→register_hint when can_execute) + recommended_action. Prefer signing swap_actions_v1 in order. MCP free; on-chain swap costs gas + integrator fee. Side effects: MCP read-only until wallet signs.

agent

get_agent_manifest

Start here: catalog of 15 terminal tools with prices, live usage stats, and journeys. Prefer get_trading_hub next. Free.

btc

get_btc_usdc_signal

Should I align with the live BTC vault? Real-time Mimo cycle LONG/SHORT/HOLD. USE WHEN: vault bias, cycle_id, open PnL (chain_snapshot), checkpoint HOLD. NOT WHEN: MM trap math (get_mm_trap_state) or hunt score alone. RETURNS: hypernatt_mimo_cycle_state_v1 — default summary v2 includes chain_snapshot, checkpoint_snapshot, interpretation_contract_v1 (PnL authority: chain only, not avg_entry). full_payload:true for per-leg detail. HOLD direction is not charged. COST: $0.001 flat via x402 (Base or Solana). Side effects: none.

entry

get_entry_quality

BTC entry-quality flags — fomo_block, anti_top_veto, early_entry, macd_exhaustion, clean_signature, accel_whale. Verdicts only. COST: $0.001. Read-only — not trade advice.

hunt

get_mm_hunt_score

Is the Market Maker hunting your position? One-line liquidation pressure summary. USE WHEN: quick hunt read, alert_level, magnet_bias. NOT WHEN: full trap/sweep math (get_mm_trap_state) or raw clusters (get_liq_radar). RETURNS: hypernatt_mm_hunt_score_v1 — mm_hunt_score (-100..100), pressure_direction, alert_level, long_trap_phase, interpretation_en. COST: $0.001 flat via x402 (Base or Solana). Side effects: none.

ignition

get_ignition

BTC ignition / micro — VID score, MRE entry score, vol spike, ADX RoC, cooldown flag. COST: $0.001. Read-only.

liq

get_liq_radar

Raw BTC liquidation radar — magnet score, OI build-up, long/short ratio, liquidation clusters above/below, 1h/24h liquidations. USE WHEN: you need the full microstructure block. Prefer get_trading_hub for a one-shot pack; agent chooses when to refresh (no mandatory poll). NOT WHEN: trap/sweep/reclaim verdicts (get_mm_trap_state) or short hunt narrative (get_mm_hunt_score). RETURNS: hypernatt_liq_radar_v1. Redacted, read-only. COST: $0.001 flat via x402 (Base or Solana). Side effects: none. Guide: github.com/DIALLOUBE-RESEARCH/hypernatt-terminal/blob/main/docs/agent-trading-hub.md

orderflow

get_orderflow

BTC orderflow — CVD, OB imbalance, icebergs bid/ask, taker ratio, funding, OI delta. Zoom tool. COST: $0.001. Read-only.

regime

get_regime

BTC regime — season/trend label, ADX, session bucket (ASIA/EU/US/LATE), F32 structure zone. COST: $0.001. Read-only.

similarity

get_similarity_match

What happened last time BTC microstructure looked like this? Top-3 historical regime matches with observed about 4h BTC outcomes (NOT vault PnL). USE WHEN: analogies / regime context only. NOT WHEN: trade direction (get_btc_usdc_signal), live trap (get_mm_trap_state), or sizing. RETURNS: hypernatt_similarity_match_v1 with interpretation_contract_v1, confidence_tier, episode_diversity, matches[]. Agents MUST quote do_not_infer rules — never treat similarity_pct as win probability. COST: $0.001 flat via x402 (Base or Solana). Side effects: none.

snapshot

get_ta_snapshot

BTC TA snapshot — RSI 15m/5m, MACD, ADX, ATR%, VWAP deviation, BB flag, velocity. Zoom tool after get_trading_hub. COST: $0.001. Read-only.

trading

get_trading_hub

One-stop BTC trading context: TA + orderflow + liq clusters above/below + hunt + regime in one call. USE WHEN: first paid context after manifest, or whenever you need a full refresh. Agent chooses cadence — no mandatory poll. NOT WHEN: you only need trap math (get_mm_trap_state) or a single zoom tool. RETURNS: hypernatt_trading_hub_v1. COST: $0.001 flat via x402. Side effects: none. Guide: github.com/DIALLOUBE-RESEARCH/hypernatt-terminal/blob/main/docs/agent-trading-hub.md

trap

get_mm_trap_state

Is the MM trapping BTC right now? Flagship Decision Core — manipulation weather (trap latch, sweep/reclaim math), not raw cluster data. USE WHEN: sizing risk or you need state (MM_TRAP_ACTIVE), trap_direction (e.g. DOWN_HUNT_LONGS), sweep_zone, chart_verdicts. NOT WHEN: one-line pressure only (get_mm_hunt_score) or raw OI/clusters (get_liq_radar). RETURNS: hypernatt_mm_trap_state_v1 — state, trap_direction, cluster_price, sweep_zone, chart_verdicts, cycles_since_trap. Read-only, not trade advice. COST: $0.001 flat via x402 (Base or Solana). Side effects: none.

vault

get_vault_proof

Free proof we eat our own cooking: on-chain vault address, public URLs, signed cycle hash. Verify our live BTC trades yourself.

Endpoints

URL	Transport	State	Latency	Checked
https://hypernatt.com/mcp/protocol	streamable-http	answering	204 ms	10 min ago
https://hypernatt.com/mcp/sse	sse	answering	171 ms	10 min ago

hypernatt-terminal — questions

Answers built from our own checks of this server.

What can hypernatt-terminal do?

It exposes 15 tools, read directly from the server on our last check. Among them: get_agent_manifest, get_btc_usdc_signal, get_entry_quality, get_ignition, get_liq_radar, get_mm_hunt_score and 9 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is hypernatt-terminal working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 182 checks got a reply (50.0%), average response time 174 ms. The bar chart above shows every period we have measured.

How do I connect hypernatt-terminal?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does hypernatt-terminal need an API key?

No. hypernatt-terminal completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 15 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is hypernatt-terminal?

It answers our handshake in 174 ms on average, which is faster than 68% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is hypernatt-terminal open source?

Yes — it is published under the MIT licence, written in JavaScript, 3 stars on GitHub and 1 open issue. The source link is on this page, so you can read exactly what it does with your data before you connect it.