TradingView MCP Server

How to use

Connect to the TradingView MCP Server using an MCP client to query market data, run technical indicators, and receive pattern analyses. You can use either a remote or a local server configuration. Start by choosing how you want to run the server, then use the client’s commands to request top gainers/losers, run Bollinger Band analyses, check RSI and MACD values, and perform multi-timeframe lookups for any symbol across supported exchanges.

How to install

Prerequisites: you need a runtime environment for running MCP servers and, if using the provided local setup, a tool to manage the server process. The recommended approach uses the UV Package Manager to run the MCP server directly from the GitHub source.

# Install UV Package Manager on macOS
brew install uv

# Install UV Package Manager on Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

# Install UV Package Manager on macOS/Linux (Direct)
curl -LsSf https://astral.sh/uv/install.sh | sh
```} ,{

Configuring the MCP server for Claude Desktop (Option 1)

Use this configuration to add the TradingView MCP Server to Claude Desktop so you can access it directly from the client.

{
  "mcpServers": {
    "tradingview-mcp": {
      "command": "uv",
      "args": [
        "tool", "run", "--from",
        "git+https://github.com/atilaahmettaner/tradingview-mcp.git",
        "tradingview-mcp"
      ]
    }
  }
}

Configuring a local MCP server (Option 2)

If you prefer running the server locally, use the following configuration to point Claude Desktop at your local Python-based server.

{
  "mcpServers": {
    "tradingview-mcp-local": {
      "command": "C:\\path\\to\\your\\tradingview-mcp\\.venv\\Scripts\\python.exe",
      "args": ["C:\\path\\to\\your\\tradingview-mcp\\src\\tradingview_mcp\\server.py"],
      "cwd": "C:\\path\\to\\your\\tradingview-mcp"
    }
  }
}

Notes for installation on macOS/Linux

For macOS or Linux environments where you install the server locally, ensure your working directory points to the repository containing the server script and you have a Python runtime available in the specified virtual environment.

Troubleshooting

Common issues include data gaps or rate limits from data providers. If you receive empty results, try different exchanges, commonly KuCoin, and standard timeframes like 15m, 1h, or 1D. If Claude Desktop does not detect the server, restart the client after updating the configuration and verify that the UV tool is installed with a valid version.

If responses are slow on the first request, warming up may be occurring; subsequent requests should be faster. For best performance, limit results to a small number of items per query.

Development & customization

Use development workflows to clone the project, install dependencies, and run in development mode to debug APIs and functions.

# Clone the repository
git clone https://github.com/atilaahmettaner/tradingview-mcp.git
cd tradingview-mcp
uv sync

# Run with MCP Inspector for debugging
uv run mcp dev src/tradingview_mcp/server.py

# Test individual functions
uv run python test_api.py

Supported capabilities and tools

The server provides a range of tools for market screening, technical analysis, information retrieval, and pattern recognition. You can run queries to identify top gainers and losers, scan for Bollinger Band squeezes, fetch Bollinger Band ratings, perform comprehensive technical analyses, and detect candlestick patterns across multiple timeframes.

Security, configuration notes and best practices

Keep your MCP endpoints secure and restrict access to trusted clients. Regularly update the server to incorporate new indicators, exchanges, and pattern recognition capabilities. When connecting from external clients, prefer authenticated connections and monitor rate limits to avoid data throttling.

top_gainers

Find highest performing assets across selected markets and timeframes.

top_losers

Identify assets with the largest declines in a given period.

bollinger_scan

Scan for assets with tight Bollinger Bands indicating potential breakouts.

rating_filter

Filter assets by Bollinger Band rating to surface signals like strong buys.

coin_analysis

Perform comprehensive technical analysis on a cryptocurrency or asset, including multiple indicators.

consecutive_candles_scan

Detect sequences of consecutive bullish or bearish candles.

advanced_candle_pattern

Analyze patterns across multiple timeframes for complex signal detection.

exchanges://list

List all supported exchanges and markets.