tradingview-mcp
Fetches OHLCV candle data for NSE/BSE symbols from TradingView's WebSocket, providing a single MCP tool to test intraday/live data before upgrading to the paid Kite Connect API.
README
tradingview-mcp
A minimal MCP server that fetches OHLCV candles for NSE/BSE symbols from TradingView's chart WebSocket. For testing live/intraday data before moving to the paid Kite feed. Protocol reverse-engineered in PROTOCOL.md.
What it does
- One tool:
get_ohlcv(symbol, resolution, bars)→ bars as[unix_time, open, high, low, close, volume], oldest first. symbol:NSE:RELIANCE,NSE:NIFTY,BSE:SENSEX, …resolution:15/60/D/W/1Mor aliases15m/hourly/daily/weekly.- Indicators are NOT fetched — compute EMA/ATR/RSI yourself (the swing engine already does).
- Data quality depends on login (see below). Logged in with a free account, many NSE symbols stream real-time; anonymous guest is delayed/EOD.
First-time login (recommended)
A logged-in session gives better/real-time data. Run this once — the password
is used only to obtain a token and is never stored; only the token +
sessionid land in .tv_session.json (gitignored, chmod 600). The client and MCP
pick it up automatically.
TV_USERNAME='you@example.com' TV_PASSWORD='...' python3 tv_auth.py
If TradingView ever throws a CAPTCHA/2FA (it didn't in testing), grab the
auth_token from a logged-in browser (devtools → WS → set_auth_token) and drop
it into .tv_session.json as {"auth_token":"..."}. Without any session file the
client falls back to the guest token automatically.
Files
tv_client.py— the WebSocket client (also runnable:python3 tv_client.py NSE:RELIANCE D 10)tv_auth.py— one-time login → saves the session token (.tv_session.json)server.py— the stdio MCP server (no external SDK; retries on TV rate-limits)requirements.txt—websocket-client,requests(login only)
Install / run
pip install -r requirements.txt
python3 tv_client.py NSE:RELIANCE 15 5 # quick sanity check
Connect to Claude Code
claude mcp add tradingview -- python3 /home/neh/StockWealth/tradingview-mcp/server.py
Restart the session so the tool loads, then ask for e.g. NSE:HFCL daily candles.
Honest caveats
- Unofficial + against TradingView's ToS; the protocol/tokens change without notice, so this WILL break eventually. Testing tool only.
- A logged-in free account streams real-time on many NSE symbols (verified); anonymous guest is delayed. Some symbols/exchanges still require a paid data plan regardless.
- TradingView rate-limits rapid reconnects; the server retries with backoff. Don't hammer it.
- The intended production path is the Kite Connect API (~₹500/mo) — official, stable, real-time. This MCP exists only to test the intraday-data workflow first.
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。