TradingView MCP Server
Provides access to TradingView data including real-time quotes, technical ratings, and historical OHLCV data for financial instruments.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@TradingView MCP Serverwhat's the quote and rating for AAPL?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
TradingView MCP Server (núcleo)
Servidor MCP construido desde cero que expone datos de TradingView vía
librerías no oficiales (tradingview-ta, tvDatafeed). Sigue el mismo
patrón de despliegue que el servidor MCP de Alpaca: Streamable HTTP
montado en /mcp, listo para Render.
Herramientas expuestas
get_quote_and_rating(symbol, exchange, screener, interval) — cotización actual + rating técnico (Comprar/Vender/Neutral) + indicadores (RSI, MACD, medias móviles, etc.)
get_historical_data(symbol, exchange, interval, n_bars) — velas OHLCV históricas.
screen_market(symbols, exchange, screener, interval) — compara el rating técnico de varios símbolos a la vez.
Related MCP server: tradingview-mcp
Variables de entorno (opcionales)
TV_USERNAME/TV_PASSWORD: credenciales de TradingView paratvDatafeed. Sin ellas funciona en modo anónimo (con más límites).PORT: puerto HTTP (Render lo inyecta automáticamente).
Correr localmente
pip install -r requirements.txt
python server.pyEl servidor queda escuchando en http://localhost:8000/mcp.
Desplegar en Render
Sube esta carpeta a un repo de GitHub.
En Render: New → Web Service → conecta el repo.
Render detecta
render.yamlautomáticamente (Build:pip install -r requirements.txt, Start:python server.py).(Opcional) configura
TV_USERNAME/TV_PASSWORDen Environment.Una vez desplegado, la URL del conector para Claude.ai es:
https://<tu-servicio>.onrender.com/mcp
Importante — limitaciones a tener en cuenta
TradingView no tiene una API pública oficial. Este servidor usa librerías no oficiales que dependen de endpoints internos y pueden romperse sin aviso si TradingView cambia su plataforma. Está pensado como núcleo funcional (cotizaciones, ratings, histórico, screener manual); funciones como alertas nativas, Pine Script o dibujos técnicos de tu cuenta no están cubiertas — requerirían ingeniería inversa adicional del WebSocket privado de TradingView.
This server cannot be deployed
Maintenance
Related MCP Connectors
Market Data App MCP — wraps the Market Data App API (marketdata.app)
MCP server for OpenMM — exposes market data, account, trading, and strategy tools to AI agents
MCP server exposing the Backtest360 engine API as tools for AI agents.
Open-source MCP server for Zerodha Kite Connect. Portfolio, market data, backtesting, alerts.
Related MCP Servers
- FlicenseAqualityCmaintenanceAn MCP server providing Model-usable tools to fetch real-time quotes, historical price charts, fundamental datasets, SEC filings, economic/earnings calendars, option chains, and corporate bond data from TradingView.21-
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol (MCP) server that lets AI assistants interact with TradingView for real-time quotes, historical OHLCV data, screener, alerts, watchlists, news, chart layouts, Pine scripts, and more. Connect it to Claude Desktop, Cursor, or any MCP-compatible client to control TradingView via natural language.132 npm5-
- AlicenseAqualityBmaintenanceMCP server for TradingView's market screener API, enabling stock, forex, crypto, and ETF screening, technical analysis, and investor workflows via Claude or CLI.12297 npm53MIT
- FlicenseBqualityDmaintenanceA TradingView-style market research and charting MCP server that provides tools for market data, indicators, watchlists, and local HTML chart rendering without scraping TradingView.9-