# tradingview-mcp [Health: Active]

**Category:** 💰 Finance & Fintech  
**Repository:** https://github.com/atilaahmettaner/tradingview-mcp  
**GitHub Stars:** 5258  
**Views:** 6  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/tradingview-mcp

## Description
Real-time market data, screeners, technical analysis & backtesting for stocks, crypto and forex.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `uvx` (confidence: high):

```json
"mcpServers": {
  "tradingview-mcp": {
    "command": "uvx",
    "args": ["tradingview-mcp-server"]
  }
}
```

## Documentation

## What tradingview-mcp does

tradingview-mcp exposes financial market research and analysis through the Model Context Protocol. It covers stocks, cryptocurrencies, forex, and futures across global exchanges, with tools for live market data, technical indicators, screeners, sentiment, and backtesting. Example requests include finding the top crypto gainers on Binance, analyzing NVDA, reviewing gold across multiple timeframes, or testing an RSI strategy on BTC daily data.

The project is intended for informational and educational analysis. It does not place trades, manage money, or provide investment, legal, tax, or accounting advice. Signals, scores, trade setups, entries, stop losses, and targets are computed from third-party data and should not be treated as recommendations.

## How it works

Market data is fetched server-side from public endpoints. The server does not log into, scrape, or automate a TradingView account, and it does not require TradingView credentials or an API key. This makes it different from MCP projects that operate the TradingView Desktop interface through browser or desktop automation.

The self-hosted server can be connected to an MCP-compatible AI application. A hosted deployment, TradingMCP, is also available at `https://mcp.tradingmcp.ai/mcp`; users connect through a private link or supported connector and sign in to the hosted service. The hosted version can render interactive candlestick charts inside the conversation, including 1-day, 1-hour, and 15-minute views with an optional Bollinger Bands overlay.

## Setup and configuration

Self-hosting is available through Python package installation, including `pip install`. The project is also presented as usable without local setup through the hosted TradingMCP service. For the hosted connection, the MCP endpoint is:

```text
https://mcp.tradingmcp.ai/mcp
```

The hosted service supports connections from Claude, Cursor, Grok, ChatGPT, Copilot, and other MCP clients according to their connector capabilities. No TradingView account or TradingView API key is needed. Hosted access is a separate paid service, while self-hosting remains free.

## Tools and capabilities

The server provides 39 tools spanning:

- Real-time market data for supported asset classes and exchanges
- Technical indicators and full technical analysis
- Multi-timeframe market analysis
- Market and asset screeners, including ranked-gainer queries
- Sentiment data
- Yahoo Finance data
- Backtesting for trading strategies
- Hosted interactive candlestick charts with optional Bollinger Bands

The exact response depends on the selected market, exchange, timeframe, and analysis request. The project can be used from Claude, ChatGPT, Cursor, Copilot, Claude Code, or another MCP client.

## Limitations and notes

Data comes from third-party public endpoints and may be delayed, inaccurate, incomplete, or unavailable. Users are responsible for complying with the terms governing any data source they use. The project is independent and is not affiliated with, endorsed by, or associated with TradingView Inc.; “TradingView” is a trademark of its respective owner.

Charts rendered inside conversations are a capability of the hosted TradingMCP deployment. The server is for analysis and research only: it does not execute orders or guarantee financial outcomes. Trading and investing involve substantial risk, so decisions require independent research and appropriate professional advice.

_Full upstream README: https://allmcps.com/mcp/tradingview-mcp/readme_