Hunter Killer

io.github.Irishman-Management-LLC由 GitHub 帳號 Irishman-Management-LLC 發布v1.0.0更新於 Nov 7, 2026

Liquidation walls, snapshot age, evidence labels and a public record. Managed OAuth.

發布方自己的服務：Hunter Lease

已驗證Streamable HTTP可網頁執行金融資料與分析

服務詳細資訊

識別碼: io.github.Irishman-Management-LLC/hunterkiller
傳輸: Streamable HTTP
執行環境: Web executable
信任: Verified
發布於: Nov 7, 2026

安全提示

MCP 服務會接收對話中的工具呼叫請求，並可能執行外部操作。啟用前請先了解該服務能做什麼，並只授予它所需的權限。

註冊中心已驗證此條目所屬的 GitHub 帳號 Irishman-Management-LLC。這並不表明該帳號就是產品方。

SourceWeft 的檢查只涵蓋條目是否完整、端點是否回應；不審查伺服器的程式碼，也不審查其工具的行為。

在 README 中新增徽章

向讀者展示該 MCP 服務已收錄於 SourceWeft，徽章連結到本頁。

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.Irishman-Management-LLC%2Fhunterkiller.svg)](https://sourceweft.com/mcp/io.github.Irishman-Management-LLC%2Fhunterkiller?utm_source=readme&utm_medium=badge)

概覽

AI 產生的概覽

遠端 MCP 端點，讓助理以唯讀方式取得加密貨幣爆倉牆、快照時效、證據標籤與公開紀錄。

可以做什麼: 讀取某個幣對的爆倉牆與最近價位，並附上快照時效與證據標籤
檢視 tier、延遲、時間戳與紀錄等欄位，並在呈現結果時一併保留
透過託管 OAuth 傳輸接入，公開主網域端點提供探索與預覽內容
可使用針對 LangChain、CrewAI、Composio 與 Node 的唯讀 HTTP 用戶端封裝與函式結構
適用情境: 適合希望助理在對話或代理流程中取得描述性加密市場結構資料（爆倉牆、價位階梯、資料新鮮度），且完全不涉及交易執行的情境。
執行需求: 需要遠端 streamable HTTP 端點，無需本機套件或環境變數。須在 MCP 用戶端完成託管 OAuth 登入，OAuth 存取權與付費資料權益彼此獨立。呼叫可能回傳 401、403、402、429 或 503。

安裝前請注意

免費資料被說明為在六個幣種上延遲 2 小時，首次呼叫仍可能回傳 401。OAuth 存取不含付費資料權益，且不會自動扣款。結果僅為描述性量測，不構成交易建議；紙上策略範例為模擬，含歷史代理輸入、成本與虧損期間，實盤執行已停用。

安裝

在 SourceWeft 中

開啟儀表板中的 Hunter Killer，將其新增到工作區。
連接所需的憑證。它們會被私密儲存，絕不會在公開頁面上展示。
為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.Irishman-Management-LLC%2Fhunterkiller/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。客戶端會在首次連接時完成 OAuth 登入。

{
  "mcpServers": {
    "hunter-killer": {
      "type": "http",
      "url": "https://agents.hunterkiller.io/mcp"
    }
  }
}

README

Hunter Killer agent examples

curl --fail-with-body --max-time 20 https://hunterkiller.io/api/v1/levels/BTCUSDT# Or, with only Python's standard library:python3 examples/one_call.py BTCUSDT

curl --fail-with-body --max-time 20 https://hunterkiller.io/api/v1/levels/BTCUSDT# Or, with only Python's standard library:python3 examples/one_call.py BTCUSDT

The keyless rollout and wrapper publication are pending a live receipt. A first call can still return 401. A failure is never labeled as successful data. No external paying use is claimed.

Read liquidation walls, snapshot age, evidence labels and a public record. The strategy examples use paper orders. Live execution is disabled. Descriptive measurements, not trading advice.

Free data is 2 hours behind on six coins. Inspect tier, delay_sec, as_of_iso, age_sec, nearest, walls, truth and record. Keep these fields with any result you show. An empty ladder is not a trading instruction. Calls can return 401, 403, 402, 429 or 503; errors must reach the caller. Internal verification must use python3 examples/one_call.py --probe so probes are not confused with external adoption.

Integrations

packages/langchain: hunterkiller-langchain, Python transport and LangChain factory.
packages/crewai: hunterkiller-crewai, CrewAI factory using the same transport.
packages/composio: hunterkiller-composio, experimental standalone session tool.
packages/npm: hunterkiller-agent-tools, Node client, LangChain factory and function definitions.
schemas/openai-function.json: strict Responses API function schema. Dispatch to the read only HTTP client.
schemas/composio-openapi.json: public REST definition for custom bindings, not a hosted catalog listing.
space: manual Gradio ladder demo for Hugging Face Spaces.
examples/sdk.py and examples/sdk.mjs: existing published SDK Desk Read examples.
examples/freqtrade: the Freqtrade paper strategy, native historical public wall proxy table and API key signup link.
examples/hummingbot: the Hummingbot paper grid and its labeled historical quote model table.
strategies: shared point in time inputs, sealed observations, full results, costs and losses.

The wrappers call the public endpoint directly because the versions of the existing SDKs currently on PyPI and npm do not expose levels. They do not compute walls or grades. Credentials, if supplied by the application, never appear in the model's argument schema. No payment is automatic.

MCP

https://agents.hunterkiller.io/mcp is the Managed OAuth transport. Complete its normal sign in flow in your MCP client. OAuth transport access and paid Hunter Killer data entitlement are separate. registry/server.json describes that hosted server, not an installable open source server implementation. The public apex https://hunterkiller.io/mcp also offers discovery and public teasers. See the current auth and tool details on the data door.

Public source and risk

Agent door, proof, privacy, risk. Never infer a future return or trade recommendation from these measurements. The paper examples retain their historical proxy inputs, costs and losing periods. Those results describe a simulation, not live performance.

來源：README.md，提交 addd58f