tradinview-mcp
A TradingView-style market research and charting MCP server that provides tools for market data, indicators, watchlists, and local HTML chart rendering without scraping TradingView.
README
tradinview-mcp
Provider-based TradingView-style market research and charting MCP server.
This project does not scrape TradingView, does not use undocumented TradingView APIs, and does not execute trades. It exposes MCP tools for market-data research, indicator calculation, watchlists, and local chart HTML rendering.
Quick Start
pnpm install
cp .env.example .env
pnpm dev
The default provider is mock, so the server works without API keys.
For the ChatGPT/Vercel-style remote endpoint locally:
pnpm dev:http
Endpoint:
http://localhost:3000/api/mcp
Real Provider Mode
mock is the safe offline default. To use real public crypto market data, enable Binance:
ENABLE_BINANCE=true
DEFAULT_PROVIDER=binance
BINANCE_BASE_URL=https://data-api.binance.vision
To make sure the server never starts accidentally with mock data:
REQUIRE_REAL_PROVIDER=true
Then run:
pnpm dev
Use the verify_provider MCP tool with:
{ "provider": "binance", "symbol": "BTCUSDT", "interval": "1h" }
That tool performs real quote and OHLCV calls and returns realProvider: true when the selected provider is not mock.
MCP Client Config
After building:
pnpm build
Add a stdio MCP server entry similar to:
{
"mcpServers": {
"tradinview-mcp": {
"command": "node",
"args": ["C:/Users/mobol/Downloads/tradinview-mcp/dist/index.js"],
"env": {
"DEFAULT_PROVIDER": "mock"
}
}
}
}
ChatGPT via Vercel
Deploy the remote MCP endpoint:
npx vercel --prod
Set Vercel env vars for real Binance data:
ENABLE_BINANCE=true
DEFAULT_PROVIDER=binance
REQUIRE_REAL_PROVIDER=true
BINANCE_BASE_URL=https://data-api.binance.vision
WATCHLIST_PATH=/tmp/watchlist.json
Then connect ChatGPT Developer Mode to:
https://your-project.vercel.app/api/mcp
See Setup for the full ChatGPT connection flow.
For development, use:
{
"mcpServers": {
"tradinview-mcp": {
"command": "pnpm",
"args": ["dev"],
"cwd": "C:/Users/mobol/Downloads/tradinview-mcp"
}
}
}
Tools
search_symbols: search configured providers.get_quote: get latest normalized quote.get_ohlcv: get OHLCV bars.calculate_indicators: calculate SMA, EMA, RSI, MACD, and Bollinger Bands.render_chart_html: render safe local Lightweight Charts HTML from supplied bars.get_watchlist: read local watchlist.add_to_watchlist: add or update a watchlist symbol.remove_from_watchlist: remove a watchlist symbol.verify_provider: perform a provider quote/OHLCV smoke check.
Example tool inputs:
{ "query": "BTC", "provider": "mock" }
{ "symbol": "BTCUSDT", "interval": "1h", "limit": 100, "provider": "mock" }
{
"bars": [
{ "time": "2026-06-23T00:00:00.000Z", "open": 100, "high": 105, "low": 99, "close": 103, "volume": 1000 }
],
"indicators": [{ "type": "SMA", "period": 20 }]
}
Resources
market://schemamarket://provider-statusmarket://compliance-notes
Prompts
analyse_symbolcompare_assetsbuild_watchlist
Optional Binance Provider
Binance is disabled unless configured:
ENABLE_BINANCE=true
DEFAULT_PROVIDER=binance
Only public crypto spot market data endpoints are used. The default Binance URL is https://data-api.binance.vision, Binance's market-data-only base endpoint.
Verification
pnpm typecheck
pnpm test
pnpm build
Run the live provider smoke test only when you want an internet-backed check:
pnpm test:live
More details:
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。