Lewati ke konten TradingView MCP Server 📈
A lightweight Model Context Protocol (MCP) server for fetching TradingView chart snapshots. Uses Playwright for efficient browser automation with persistent sessions and cookie-based authentication.
Note : This uses Playwright because TradingView renders charts client-side with JavaScript/Canvas. There is no pure HTTP API for chart images. This is the lightest possible working solution (~150MB RAM vs ~500MB with Selenium).
A lightweight Python MCP server that fetches TradingView chart snapshots using Playwright for fast, secure, and customizable browser automation.
Hubungkan alat apa pun ke agen apa pun. Direktori MCP untuk yang tidak menulis server.
Produk
Direktori
Pengembang
Perusahaan
✨ Features
🪶 Lightweight : Playwright in headless mode (~150MB vs ~500MB with Selenium)
🚀 Fast : Persistent browser reuse, 3-5 seconds per chart
🔐 Secure : Session-based authentication via cookies
🎨 Customizable : Configure chart dimensions, intervals, and themes
🔧 MCP Compatible : Works with any MCP-enabled client (Claude Desktop, etc.)
♻️ Efficient : Reuses browser instances across multiple requests
📋 Prerequisites
Python 3.10 or higher
A TradingView account (free or paid)
TradingView session cookies
Table of Contents
🚀 Installation
1. Clone the repository git clone https://github.com/yourusername/tradingview-mcp.git
cd tradingview-mcp
2. Create a virtual environment # Windows
python -m venv venv
.\venv\Scripts\activate
# Linux/Mac
python3 -m venv venv
source venv/bin/activate
3. Install dependencies pip install -r requirements.txt
# Install Playwright browsers (one-time setup, ~150MB download)
python -m playwright install chromium
4. Configure credentials
Copy .env.example to .env:
# Windows
copy .env.example .env
# Linux/Mac
cp .env.example .env
Get your TradingView session cookies:
Log into TradingView in your browser
Press F12 to open Developer Tools
Go to Application tab (Chrome) or Storage tab (Firefox)
Navigate to Cookies > https://www.tradingview.com
Find and copy these two cookie values:
sessionid → Copy the entire value
sessionid_sign → Copy the entire value
⚠️ Important : Copy the full values including any special characters (slashes, equals signs, etc.). Don't add quotes or extra spaces.
Edit .env and paste your values:
TRADINGVIEW_SESSION_ID=your_actual_session_id_here
TRADINGVIEW_SESSION_ID_SIGN=your_actual_session_id_sign_here
Example (with fake values):
TRADINGVIEW_SESSION_ID=47zlhkbl2weohrhmjgufeg1o24droaod
TRADINGVIEW_SESSION_ID_SIGN=v3:6S2OD9ta349/yqN0RdCeK3UKxTl/tJr4AOoPRUa0Crk=
5. Test your setup (Optional but recommended) Create a test file test.py:
import asyncio
import sys
from pathlib import Path
sys.path.insert(0, str(Path(__file__).parent / "src"))
from dotenv import load_dotenv
load_dotenv()
from tradingview_mcp.server import get_chart_snapshot
async def test():
image = await get_chart_snapshot("BINANCE:BTCUSDT", "D", 1200, 600, "dark")
if image:
Path("test_chart.png").write_bytes(image)
print(f"✅ Success! Chart saved to test_chart.png ({len(image)} bytes)")
else:
print("❌ Failed to fetch chart")
asyncio.run(test())
If successful, you'll see test_chart.png with a Bitcoin chart!
🎯 Usage
Quick Start - Testing Locally After installation, test the server:
python src/tradingview_mcp/server.py
The server will start and wait for MCP client connections via stdio.
Configuration for Claude Desktop Add this to your Claude Desktop config file:
Windows : %APPDATA%\Claude\claude_desktop_config.json
macOS : ~/Library/Application Support/Claude/claude_desktop_config.json
Linux : ~/.config/Claude/claude_desktop_config.json
Option 1: Using .env file (Recommended)
{
"mcpServers": {
"tradingview": {
"command": "python",
"args": ["C:\\path\\to\\tradingview-mcp\\src\\tradingview_mcp\\server.py"],
"cwd": "C:\\path\\to\\tradingview-mcp"
}
}
}
Option 2: Inline credentials
{
"mcpServers": {
"tradingview": {
"command": "python",
"args": ["C:\\path\\to\\tradingview-mcp\\src\\tradingview_mcp\\server.py"],
"env": {
"TRADINGVIEW_SESSION_ID": "your_session_id",
"TRADINGVIEW_SESSION_ID_SIGN": "your_session_id_sign"
}
}
}
}
💡 Tip : Use absolute paths. On Windows, use double backslashes \\ or forward slashes /.
Restart Claude Desktop and you'll see the TradingView tools available!
Example Queries in Claude Once configured, you can ask Claude:
- "Get me a daily chart of Bitcoin"
- "Show me AAPL on 1-hour timeframe"
- "Fetch a weekly chart for NASDAQ:TSLA with light theme"
- "Get BINANCE:ETHUSDT 5-minute chart"
- "Validate my TradingView session"
- "What timeframes are available?"
🛠️ Available Tools
1. get_chart_snapshot Fetch a TradingView chart snapshot.
symbol (required): Trading pair in TradingView format
Examples: "BINANCE:BTCUSDT", "NASDAQ:AAPL", "BITSTAMP:BTCUSD"
interval (optional): Chart timeframe (default: "D")
Minutes: "1", "5", "15", "30", "60", "240"
Days/Weeks/Months: "D", "W", "M"
width (optional): Image width in pixels (default: 1200)
height (optional): Image height in pixels (default: 600)
theme (optional): "dark" or "light" (default: "dark")
Get me a daily chart of Bitcoin on Binance
2. validate_session Check if your TradingView session credentials are valid.
Validate my TradingView session
3. list_timeframes List all available chart timeframes/intervals.
What timeframes are available?
📊 Symbol Format TradingView uses the format: EXCHANGE:SYMBOL
Common Examples
Finding Symbol Names
Go to TradingView
Search for your desired asset
Look at the URL or chart title for the format EXCHANGE:SYMBOL
🔧 Architecture This MCP server uses Playwright for lightweight browser automation :
Authentication : Session cookies passed to browser context
Chart Generation : Playwright navigates to TradingView and captures screenshots
Efficiency : Persistent browser instances reused across requests
MCP Protocol : Communicates via stdio with MCP clients
Why Playwright (Not Pure HTTP)?
TradingView renders charts client-side with JavaScript/Canvas
No server-side API exists for chart image generation
Playwright is lighter than Selenium (~150MB vs ~500MB RAM)
Headless mode with optimized flags minimizes resource usage
Browser reuse makes subsequent requests very fast (1-2 seconds)
✅ This is the lightest possible approach for TradingView charts
🐛 Troubleshooting
Cookie/Authentication Issues Problem : "Session credentials are not working" or "Invalid session"
Check for trailing commas or spaces : Make sure your .env file has no extra characters
# ❌ Wrong (has comma)
TRADINGVIEW_SESSION_ID=abc123,
# ✅ Correct
TRADINGVIEW_SESSION_ID=abc123
Refresh cookies : Session cookies expire after ~30 days
Log out and back into TradingView
Get fresh cookies from Developer Tools
Update your .env file
Check you're logged in : Make sure you're logged into TradingView when copying cookies
Copy entire value : Include special characters (=, /, :, etc.)
Symbol Not Found Problem : "Failed to fetch chart snapshot"
Use correct format: EXCHANGE:SYMBOL (all uppercase)
✅ BINANCE:BTCUSDT
❌ btcusdt or binance:btcusdt
Verify symbol exists on TradingView.com
Test with a known symbol first: BINANCE:BTCUSDT or NASDAQ:AAPL
Timeout Errors Problem : "Timeout exceeded" or slow performance
Check internet connection and TradingView.com accessibility
First request takes longer (5-8s) while browser starts
Subsequent requests are faster (3-5s) due to browser reuse
If persistent, restart the MCP server
Playwright Installation Issues Problem : "Playwright not found" or browser download fails
# Reinstall Playwright
pip uninstall playwright
pip install playwright
# Install browsers again
python -m playwright install chromium
# If still failing, install system dependencies (Linux)
sudo playwright install-deps
Claude Desktop Not Recognizing Server Problem : Tools don't appear in Claude Desktop
Check JSON syntax in config file (use a JSON validator)
Use absolute paths (not relative)
Verify Python path is correct:
# Windows
where python
# Mac/Linux
which python
Completely restart Claude Desktop (not just reload)
Check Claude logs for errors:
Windows: %APPDATA%\Claude\logs\
Mac: ~/Library/Logs/Claude/
Performance Issues Problem : High memory usage or slow responses
Memory usage: ~150MB is normal for Playwright
First chart: 5-8 seconds (browser startup)
Subsequent charts: 3-5 seconds
Browser is reused across requests for efficiency
If memory grows over time, restart the server
⚡ Performance Comparison with Alternatives:
🔒 Security Notes
⚠️ Never commit your .env file - it contains your session credentials
⚠️ Don't share your session cookies - they provide full account access
⚠️ Rotate cookies regularly - they expire after ~30 days
✅ .env is in .gitignore by default
✅ Use environment variables or secure credential management in production
📝 Development
Project Structure tradingview-mcp/
├── src/
│ └── tradingview_mcp/
│ ├── __init__.py
│ └── server.py # Main MCP server
├── .env.example # Template for credentials
├── .gitignore
├── README.md
├── requirements.txt # Python dependencies
└── pyproject.toml # Project metadata
Running Tests # Install dev dependencies
pip install -e ".[dev]"
# Run tests
pytest
Code Formatting # Format code
black src/
# Lint code
ruff check src/
🤝 Contributing Contributions are welcome! Here's how:
Fork the repository
Create a feature branch (git checkout -b feature/amazing-feature)
Make your changes
Test thoroughly
Commit your changes (git commit -m 'Add amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request
pip install -e ".[dev]"
black src/
ruff check src/
📄 License MIT License - see LICENSE file for details.
🙏 Acknowledgments
⚠️ Disclaimer This is an unofficial tool and is not affiliated with, endorsed by, or connected to TradingView. Use at your own risk and in accordance with TradingView's Terms of Service. Respect rate limits and be mindful of your usage.
� Support & Issues
📊 Project Stats
Version : 0.1.0
Python : 3.10+
Memory : ~150MB
Response Time : 3-5 seconds
License : MIT
Made with ❤️ by the trading community
Star ⭐ this repo if you find it useful!
Skor direktori 14/100 Terdaftar 10 dari 10
Ada di MCP Registry resmi 0 dari 18
Diklaim oleh maintainer 0 dari 8
Merespons dengan daftar tool 0 dari 12
Bintang GitHub 8 dari 16
Unduhan mingguan 0 dari 10
Scrapling 🕷️ The BEST Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and trick Chrome Devtools Chrome DevTools for coding agents Chrome DevTools MCP MCP server for Chrome DevTools Chrome DevTools MCP MCP server for Chrome DevTools Chrome Devtools Chrome DevTools for coding agents UI TARS Desktop The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra Playwright Playwright MCP server Playwright Playwright MCP server Obscura The headless browser for AI agents and web scraping Cua Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation. Ego Lite The fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state with your AI agents, like Codex or Claude Code, without disturbing you. Zero cost, zero conf SeleniumBase 📊 Python APIs for Web Automation, Testing, and Scraping. CDP Mode launches a stealth browser that bypasses bot-detection/CAPTCHAs. Adds stealth to Playwright and has an MCP server for AI agents. Server MCP Browser automation Server MCP Browser automation terbaik
Belum ada daftar tool. Server remote mendapatkannya setelah pemeriksaan kesehatan pertama.
Bagaimana cara menginstal Tradingview? Salin konfigurasi stdio untuk Cursor, Claude Desktop, Claude Code, atau VS Code di halaman ini. Konfigurasi ini memakai instalasi dari penerbit, bukan proxy PlugMCP.
Apakah Tradingview memerlukan kunci API? Tidak ada variabel lingkungan wajib yang tercantum di catatan ini.
Transport apa yang digunakan Tradingview? Tradingview berjalan secara lokal melalui stdio.
Kapan Tradingview terakhir diperiksa? Terakhir diperiksa 2026-10-28. A lightweight Python MCP server that fetches TradingView chart snapshots using Playwright for fast, secure, and customizable browser automation.
Tool memiliki deskripsi 0 dari 6
Tidak terlihat selama tiga hari -8