TradeOS (test)

io.github.TradeOS-AI由 GitHub 帳號 TradeOS-AI 發布v1.0.0-alpha.6更新於 Nov 9, 2026

[TEST] TradeOS MCP bridge: ticker search, My Agent, chart TA, macro news. npm or HTTP.

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取金融資料與分析

概覽

AI 產生的概覽

TradeOS MCP 將 TradeOS 交易情報接入 AI 助理，支援代碼搜尋、行情分析、價差比較、總體新聞與自訂交易代理。

可以做什麼
  • 搜尋交易代碼並查詢市場標的
  • 分析圖表與技術指標
  • 比較價差並取得總體新聞背景
  • 建立與管理自訂交易代理（My Agent）
  • 透過 HTTP 或本機 stdio 橋接將上述能力代理到 TradeOS 遠端端點
適用情境
適合想用自然語言讓助理研究行情、比較價差、進行技術與總體分析，並集中管理自訂交易代理的使用者。已擁有具備 MCP API 存取權限的 TradeOS 帳戶時最合適。
執行需求
兩種方式：使用遠端 HTTP 端點並由用戶端完成瀏覽器 OAuth；或在本機執行 npm 套件，需要 Node.js 18+ 以及透過 OAuth 輔助工具取得的 TRADEOS_ACCESS_TOKEN 環境變數。需要具備 MCP API 存取權限的 TradeOS 帳戶。Windows 上 README 建議以固定目錄本機安裝而非使用 npx。
安裝前請注意
npm 模式需要 TradeOS 存取權杖（TRADEOS_ACCESS_TOKEN），請勿提交到版本庫或與他人共用的用戶端設定中。此伺服器可建立與管理交易代理，操作可能影響你的 TradeOS 帳戶。行情分析不構成投資建議，提示與資料會傳送至 TradeOS 服務。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 TradeOS (test)，將其新增到工作區。
  2. 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.TradeOS-AI%2Ftradeos-mcp-test/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。

{
  "mcpServers": {
    "tradeos-test": {
      "type": "http",
      "url": "https://ai.tradeos.xyz/api/agent/mcp-call"
    }
  }
}

README

tradeos-mcp

TradeOS MCP lets you connect TradeOS trading intelligence to MCP-compatible AI tools, so your assistant can analyze markets, search tickers, compare spreads, use macro context, and manage custom trading agents directly from natural-language prompts.

Overview

This repo publishes @tradeos/tradeos-mcp on npm: a stdio MCP bridge that proxies tools to TradeOS Streamable HTTP (mcp-call). You can connect in two ways:

ModeBest forAuth
HTTP (recommended)Cursor, Claude Code, most MCP clientsBrowser OAuth in the client
npm stdioClients that only support command / stdioTRADEOS_ACCESS_TOKEN env var

Production endpoint (both modes ultimately call this):

text
https://ai.tradeos.xyz/api/agent/mcp/mcp-call

Product docs: TradeOS MCP integration & usage

Prerequisites

  • Node.js 18+
  • A TradeOS account with MCP API access
  • For npm stdio: ability to run a local install (see Windows notes)

Option A — HTTP (recommended)

No npm install. The client handles OAuth.

Cursor

Edit user config ~/.cursor/mcp.json (Windows: %USERPROFILE%\.cursor\mcp.json):

json
{  "mcpServers": {    "tradeos": {      "url": "https://ai.tradeos.xyz/api/agent/mcp/mcp-call"    }  }}

Save, restart Cursor (or refresh MCP in Settings → MCP), then complete OAuth when prompted.

Claude Code (plugin — recommended)

Use the bundled plugin in tradeos-skills/:

bash
claude --plugin-dir ./tradeos-skills

Then complete OAuth and run /tradeos:analyze. Full plugin workflow (validate, community marketplace submit): tradeos-skills/README.md — aligned with Claude plugin docs.

Option B — npm stdio bridge

Use when your client requires a local process (command + stdio).

1. Install locally

Do not rely on npx inside MCP on Windows (cache/path issues). Install once to a fixed directory:

bash
mkdir -p ~/tradeos-mcp-run   # Windows: mkdir %USERPROFILE%\Downloads\tradeos-mcp-runcd ~/tradeos-mcp-run         # Windows: cd %USERPROFILE%\Downloads\tradeos-mcp-runnpm install @tradeos/tradeos-mcp

Pin a version if you prefer, e.g. @tradeos/[email protected].

2. Get TRADEOS_ACCESS_TOKEN

Run the OAuth helper (opens browser → log in on TradeOS → prints token):

bash
# Linux / macOSnpx -y -p @tradeos/tradeos-mcp tradeos-mcp-oauth
# Or subcommand on main bin:npx -y @tradeos/tradeos-mcp oauth
# Or, from your install directory:node node_modules/@tradeos/tradeos-mcp/scripts/fetch-token.mjs

Windows (recommended):

cmd
cd /d %USERPROFILE%\Downloads\tradeos-mcp-runnode node_modules\@tradeos\tradeos-mcp\scripts\fetch-token.mjs

Copy the printed JWT (eyJ...). For local development of this repo, copy into .env:

bash
cp .example.env .env# TRADEOS_ACCESS_TOKEN=eyJ...

End users who only npm install the package do not need .env — set the token in MCP client config (mcp.json) instead.

Do not commit tokens to git.

3. Configure Cursor

json
{  "mcpServers": {    "tradeos-npm": {      "command": "node",      "args": [        "C:/Users/YOU/Downloads/tradeos-mcp-run/node_modules/@tradeos/tradeos-mcp/build/index.js"      ],      "env": {        "TRADEOS_ACCESS_TOKEN": "eyJ..."      }    }  }}

Replace YOU and the path with your actual install location. Use forward slashes or escaped backslashes in JSON.

If Cursor cannot find node, set the full path:

json
"command": "C:/nvm4w/nodejs/node.exe"

Enable tradeos-npm in Settings → MCP. Status should show connected with tools listed.

4. Verify in terminal (optional)

Environment variables in mcp.json do not apply to your shell. Set the token in the same terminal session:

cmd
REM Windows CMDset TRADEOS_ACCESS_TOKEN=eyJ...node C:\Users\YOU\Downloads\tradeos-mcp-run\node_modules\@tradeos\tradeos-mcp\build\index.js
bash
# Linux / macOSexport TRADEOS_ACCESS_TOKEN=eyJ...node ~/tradeos-mcp-run/node_modules/@tradeos/tradeos-mcp/build/index.js

Success:

text
[tradeos-mcp] remote: https://ai.tradeos.xyz/api/agent/mcp/mcp-call[tradeos-mcp] stdio bridge ready

Press Ctrl+C to stop. Cursor starts its own process; you do not need to keep this terminal open.

Windows notes

  1. Use local node + install path in mcp.json, not npx, for MCP.
  2. If npm cache errors mention C:\Program Files\nodejs\node_cache, run once:
    cmd
    npm config set cache "%USERPROFILE%\.npm-cache"
  3. npx @pkg tradeos-mcp-oauth may run the wrong bin on Windows. Prefer:
    cmd
    npx -y -p @tradeos/tradeos-mcp tradeos-mcp-oauth
    or node .../scripts/fetch-token.mjs from your install directory.
  4. Clear a broken npx cache (quit Cursor first):
    cmd
    rmdir /s /q "%USERPROFILE%\.npm-cache\_npx"

npm package reference

ItemValue
Package@tradeos/tradeos-mcp
MCP Registry nameio.github.TradeOS-AI/tradeos-mcp
Bin: MCP bridgetradeos-mcp
Bin: OAuth tokentradeos-mcp-oauth
OAuth subcommandoauth on bin tradeos-mcp

Install:

bash
npm install @tradeos/tradeos-mcp

Development (this repo)

bash
git clone https://github.com/TradeOS-AI/tradeos-mcp.gitcd tradeos-mcpnpm cinpm run buildnpm run oauth:token    # browser OAuth → prints token (copy into .env if needed)npm run registry:verify
ScriptPurpose
npm run buildCompile stdio bridge to build/
npm run oauth:tokenBrowser OAuth → print token
npm run registry:verifyPre-publish checks (package.json ↔ server.json)
npm run registry:sync-version <ver>Sync version from release tag

Publishing (maintainers)

Push a version tag to trigger .github/workflows/publish-mcp.yml:

bash
git tag v1.0.0git push origin v1.0.0
  • Stable tags (v1.0.0) publish to npm latest and the MCP Registry.
  • Pre-release tags (v1.0.0-beta.1) publish with an npm dist-tag matching the prerelease label (e.g. beta).
  • Requires GitHub Actions secret NPM_TOKEN (Classic Automation token for @tradeos).

Verify on the registry API:

bash
curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.TradeOS-AI/tradeos-mcp"

Troubleshooting

SymptomLikely causeFix
TRADEOS_ACCESS_TOKEN is requiredToken not set in env / mcp.jsonRun oauth helper; set env in MCP config
unauthorized on connectExpired or invalid tokenRe-run oauth; paste fresh JWT (no Bearer prefix)
EPERM / node_cachenpm cache under Program Filesnpm config set cache "%USERPROFILE%\.npm-cache"
TAR_ENTRY_ERROR / 'tradeos-mcp' is not recognizednpx failed on WindowsLocal install + node path in mcp.json
MODULE_NOT_FOUND for node_modules/...Ran script from wrong directorycd to install dir or use absolute path
Token works in terminal, not in Cursormcp.json path or token mismatchMatch paths; restart Cursor / refresh MCP
MCP connects but no toolsWrong server enabledDisable broken localhost entries; use production HTTP URL or working tradeos-npm

Related

來源：README.md，提交 2b620e3

工具

0
SourceWeft 尚未讀取此伺服器的工具。

版本歷史

1
  1. v1.0.0-alpha.6最新Sep 16, 2026

評分

已滿足適用檢查項的 85%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具必需15 分

    請讓伺服器在無憑證時回應 tools/list，或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分