GitHub
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
제작자가 쓴 설명(영어 원문)
Liquidation radar, execution context and Li.Fi swaps for AI agents. 6 MCP tools; x402 payments.
이 세 가지는 절대 하나의 점수로 합치지 않아요. 의견, 측정, 인기는 서로 다른 것이니까요.
이 서버는 아직 쉬운 말로 된 요약을 쓰지 못했어요. 아래는 레지스트리에서 읽어 온 사실이에요.
쓰고 있는 AI 앱을 고른 다음 설정을 복사하세요.
필요한 것
어떤 앱을 쓰세요?
위에서 앱을 고르세요. 기억해 두었다가 다음부터는 버튼에 “…에 설치”라고 표시해요.
웹, 데스크톱, 모바일의 Claude에서 쓸 수 있어요:
https://hypernatt.com/mcp/protocol터미널에서 이 명령어를 실행하세요
claude mcp add --transport http hypernatt-terminal https://hypernatt.com/mcp/protocol프로젝트의 .cursor/mcp.json 또는 ~/.cursor/mcp.json에 붙여 넣으세요
{
"mcpServers": {
"hypernatt-terminal": {
"url": "https://hypernatt.com/mcp/protocol"
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
프로젝트의 .vscode/mcp.json에 붙여 넣으세요
{
"servers": {
"hypernatt-terminal": {
"type": "http",
"url": "https://hypernatt.com/mcp/protocol"
}
}
}브라우저가 앱을 열지 물어본 다음, 앱이 설정을 보여 주고 확인을 요청해요. 키 값은 비워 두니 직접 입력하세요.
ChatGPT는 인터넷에 있는 서버에만 연결할 수 있어요:
https://hypernatt.com/mcp/protocol메뉴 이름은 요금제나 시기에 따라 조금 다를 수 있어요.
선택한 앱은 이 기기의 쿠키에만 저장돼요. 계정은 필요 없어요.
이 설정은 제작자의 레지스트리 정보로 만들었어요. README와 다르면 README를 따르세요.
아직 이 서버의 도구 목록을 읽지 않았어요. 엔드포인트는 차례대로 돌아가며 점검해요.
누구나 볼 수 있는 정보를 점검했고, 코드는 읽지 않았어요. 해당하지 않는 항목은 개수에서 뺐어요. · 2026년 11월 9일 점검
레지스트리 이름이 GitHub 계정 DIALLOUBE-RESEARCH 기준으로 확인되었고, 이 계정이 저장소를 소유하고 있어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 GitHub에서 이 저장소를 읽어 오지 않았어요
아직 점검하지 않았어요. 엔드포인트는 차례대로 돌아가며 점검해요
아직 점검하지 않았어요. 엔드포인트는 차례대로 돌아가며 점검해요
아직 점검하지 않았어요. 엔드포인트를 점검할 때 도구 목록을 읽어요
레지스트리에서 이 카테고리의 활성 서버 전체와 비교했어요. 스타는 게시자가 저장소를 소유한 경우에만 세요.
해당하는 기본 점검 1개 중 1개를 통과했어요. 코드는 읽지 않았어요. 키나 토큰을 넣기 전에 서버가 어떤 권한을 요구하는지 확인하고, 꼭 필요한 권한만 있는 키를 쓰세요.
레지스트리에 필수 키가 나와 있지 않아요. 다만 처음 쓸 때 로그인을 요구하는 서버도 있어요.
제작자의 클라우드에서 실행돼요. 설치 없이 인터넷으로 연결하지만, 보내는 내용은 제작자의 서버를 거쳐요.
GitHub 저장소는 마지막으로 – 변경됐고, 최신 버전(2.8.0)은 2개월 전 레지스트리에 올라왔어요.
Claude Desktop, Claude Code, Cursor, VS Code처럼 MCP를 지원하는 앱에서 쓸 수 있어요. URL로 연결되기 때문에, 원격 MCP 서버를 지원하는 앱(예: 개발자 모드의 ChatGPT)에서도 쓸 수 있어요.
같은 카테고리에는: GitHub, Desktop Commander, Cloudflare MCP
같은 카테고리에서 다른 제작자가 만든 서버예요. 스타 순으로 정렬했어요.
카드 보는 법:↓ 주간 다운로드i★ GitHub 스타i세 기둥: 리뷰 · 점검 · 사용 정도i업데이트 = 최신 버전을 레지스트리에 공개한 날i
Connect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
MCP server for terminal commands, file operations, and process management
제작자의 저장소에서 쓰인 그대로 가져왔어요. PopNx MCP가 검토하거나 보증한 내용이 아니에요. HTML, 이미지, 스크립트는 제거했어요. 링크를 누르면 이 사이트를 벗어나요.
Liquidation radar (7 tokens) and recorded liquidity, wall history and aggressor flow (BTC and ETH) for AI agents + Li.Fi cross-chain swap. Pay-per-call via x402.
Understand liquidation terrain, then ask whether a BTC or ETH size is feasible on the filmed book (REF plus separate aggregated views and recorded history). For cross-chain swaps, request a Li.Fi route that your agent signs. Your agent chooses the task and controls execution.
Built by one person. Code is public. Backend is private. No custody. Not trade advice.
Full HyperNatt platform (vault, assistant): https://hypernatt.com — this repo is one agent-facing brick.
Public runtime and docs are synced from the monorepo. Repository: https://github.com/DIALLOUBE-RESEARCH/hypernatt-terminal.
No install for the hosted MCP. In Claude → Settings → Connectors → Add custom connector:
| Field | Value |
|---|---|
| Name | HyperNatt Terminal |
| URL | https://hypernatt.com/mcp/protocol |
Then ask:
Call get_agent_manifest and choose journeys_v1 for my task. Use get_liq_radar for liquidation terrain. For an ETH buy of 0.1 ETH, walk filmed recorded liquidity context with get_native_depth. Use swap_via_nattswap for a Li.Fi route.
More clients (Cursor / Cline / Codex / Windsurf): docs/integrations.md.
Start with `get_agent_manifest` (free), then choose the tools your task needs through journeys_v1:
get_liq_radar provides liquidation clusters, open-interest context and observed liquidations (BTC ETH SOL BNB XRP HYPE ZEC).get_native_depth reports fill, remaining and four simultaneous views, fixed-price wall history and observed aggressor flow.swap_via_nattswap requests a Li.Fi route for your source/destination chains and tokens. Your agent signs the transaction.Radar covers seven tokens. Native depth is BTC and ETH only. Cross-chain swaps use the chains and tokens supported by Li.Fi, subject to route availability. Neither paid tool requires the other.
get_liq_radarA map of forced orders: where leveraged positions will be liquidated if price reaches them (clusters, OI build-up, observed liquidations).
This is market structure context, not a trade signal. It shows terrain so a sovereign trading agent can judge timing, sizing, and risk with more awareness than agents that only read RSI/MACD-style public feeds.
Your agent still decides. We show the terrain.
Ignore clusters with class=noise (distance < 3%). If cluster_grammar is present, wait only near class=true (low-leverage stack ~7%+). Then watch real_liquidations print — without assuming a guaranteed reversal. class=true is terrain, not an entry signal.
Cluster ~5% away vs ~0.5% away is a different risk parameter. Distance informs sizing or patience — it is not a prediction that the level will be hit.
If price swept a zone and real liquidations spiked, compare with OI change. A large OI drop can mean forced flow is partly exhausted — still context, not an auto entry.
| Term | Meaning |
|---|---|
| Cluster | Zone where leveraged positions may liquidate if mark reaches it. Not a TP. |
cluster_grammar / class | If present: read this first. noise = distance < 3% (ignore); true = ~7%+ (low-leverage stack). Not a trade signal. |
| Nearest vs largest | nearest_* is a legacy alias of largest_* (size leader), not closest-to-mark. |
| Real vs estimated | real_liquidations = observed; liq_density clusters = modeled. Both labeled. |
magnet.score | Directional density bias from OI / L-S / funding. Not a hit probability. |
The radar glossary and scenarios also ship on get_agent_manifest → agent_interpretation_rules_v1. Use journeys_v1 for native-depth and swap workflows.
get_native_depth“Where is liquidity, is it changing, and what flow is meeting it?” Supply symbol (BTC or ETH), side, quantity_base, and lookback_s (30 or 300). Read agent_readout, then liquidity_map for four simultaneous price granularities, size coverage and changes at fixed wall prices; trade_flow shows observed aggressor buying/selling. Check history coverage and freshness. Never sum overlapping views. These facts complement radar terrain without disclosing a strategy or guaranteeing a fill. Guide.
swap_via_nattswap“What route is available to swap my token on one chain for a token on another?” Supply the source/destination chains and tokens, amount and wallet addresses. Review the Li.Fi route, costs and execution readiness; your agent signs with its own wallet. This is a separate workflow from native BTC/ETH depth. Swap inputs and execution steps.
Daily MCP trial: one free call per paid tool and eligible token each UTC day: radar x 7 tokens plus native BTC/ETH, up to 9 independent trials; then 0.001 USDC per call. Read trial_policy_v2 and free_tier_status_v1 on the same MCP connection for current availability. A zero daily_cap is the separate credit pool, not the intro allowance.
| Tool | Price |
|---|---|
get_agent_manifest | Free — call first |
get_liq_radar | $0.001 x402 (Base EIP-3009 or Solana SVM exact) |
swap_via_nattswap | Free at MCP (you sign; gas + Li.Fi fee on-chain) |
get_native_depth | $0.001 x402, or eligible credits |
Solana pay: rail is live (SVM exact). Do not reuse an EVM/Base x402 client. Use @x402/svm. A Base HTTP 200 is not a Solana payment. See docs/x402-pay.md.
Whitelist get_liq_radar: BTC ETH SOL BNB XRP HYPE ZEC (omit symbol = BTC). get_native_depth: BTC ETH only.
| We do not claim | What we do show |
|---|---|
| Generic Coinglass wrapper | Operator-shaped forced-order map for agents |
| Predictive Fuel Score / sweep classifier | Distance, size, OI, real liqs — labeled |
| Custody of keys or funds | Agent signs own txs |
| Trade advice / guaranteed edge | Read-only JSON context |
| More than 4 MCP tools | Exactly 4 · v2.9.1 |
Vault / /stats = Terminal P&L | Separate HyperNatt vault product |
| Independent security audit | Public code + SECURITY.md |
curl -s https://hypernatt.com/api/m2m/agent/manifest
curl -i https://hypernatt.com/api/m2m/liq-radar
| Step | Link |
|---|---|
| Quickstart | docs/quickstart.md |
| x402 Base vs Solana | docs/x402-pay.md |
| Integrations (5 clients + AgentKit) | docs/integrations.md |
| HL terrain example (read-only) | examples/hyperliquid/read_terrain.py |
| Honest interpret example | examples/liq_radar_interpret.py |
| CDP Bazaar checklist | docs/cdp-bazaar-checklist.md |
| Examples | examples/ |
| Security | SECURITY.md |
| Buyer skill (use the MCP) | skills/hypernatt-terminal/SKILL.md |
| Seller skill (x402 hardening) | solana-x402-seller-security-skill |
| Tests | test/ — npm test |
| Changelog | CHANGELOG.md |
MCP: https://hypernatt.com/mcp/protocol
You can start with the daily MCP trials without setting up payments. For paid use, one optional wallet provider is Coinbase Agentic Wallet MCP. Follow its current setup and funding instructions; available funding methods depend on the provider and your account:
npx @coinbase/payments-mcp
Docs: Agentic Wallet MCP. Then connect HyperNatt Terminal (https://hypernatt.com/mcp/protocol). The two paid tools — get_liq_radar and get_native_depth — each cost 0.001 USDC per call, or one eligible credit, after an available daily trial. An x402-capable client can handle the payment requirements and retry under your payment authorization rules. In MCP, inspect the tool response for payment requirements; do not rely only on an HTTP 402 status. See payment and credits.
Optional: eligible swap-earned credits or an Agent Pass at $5 for 15,000 credits valid for 30 days, shared across the paid tools. Call get_agent_manifest with {"detail":"full"} to read the current pass_program and quota_program; they are not included in the default compact response. Manifest and MCP swap requests remain free; on-chain swap costs are separate.
MIT — see LICENSE.