TradingView

v1.0.0Finance & Fintechstable

A Model Context Protocol (MCP) server that provides programmatic access to TradingView's technical indicators and market data for automated trading analysis and strategy development.

mcp-tradingviewmcpai-integration
Share:
19
Stars
0
Downloads
0
Weekly
0/5

What is TradingView?

TradingView is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol (mcp) server that provides programmatic access to tradingview's technical indicators and market data for automated trading analysis and strategy development.

A Model Context Protocol (MCP) server that provides programmatic access to TradingView's technical indicators and market data for automated trading analysis and strategy development.

This server falls under the Finance & Fintech category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A Model Context Protocol (MCP) server that provides programm

Use Cases

Access TradingView technical indicators and market data programmatically. Develop and analyze trading strategies using AI. Execute automated trading analysis and backtesting.
bidouilles

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedApr 15, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx mcp-tradingview

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use TradingView

The TradingView MCP server provides Claude with programmatic access to TradingView's technical indicators and historical OHLCV market data, enabling AI-assisted trading analysis and strategy development. It exposes tools to fetch full indicator snapshots, retrieve specific technical indicators by name, and stream historical candlestick data for any symbol and timeframe supported by TradingView. Quantitative analysts and traders use it to automate chart analysis, backtest strategy ideas, and interpret market signals through natural language conversations with Claude.

Prerequisites

  • Python 3.11 or higher
  • uv package manager installed (astral.sh/uv)
  • Access to TradingView data (the server uses TradingView's data feed, no personal API key required for basic use)
  • An MCP-compatible client such as Claude Desktop
  • Git to clone the repository (for manual setup)
1

Clone the repository

Clone the mcp-tradingview-server repository to your local machine.

git clone https://github.com/bidouilles/mcp-tradingview-server.git
cd mcp-tradingview-server
2

Run the automated setup script

The setup.sh script installs Python dependencies, creates a virtual environment, and automatically updates your Claude Desktop configuration.

chmod +x setup.sh && ./setup.sh
3

Or install manually with uv

If you prefer manual setup, create a virtual environment with uv and install the package in editable mode.

uv venv --python 3.11
source .venv/bin/activate
uv pip install -e .
4

Add to Claude Desktop configuration

Add the server to your claude_desktop_config.json using the Claude CLI or by editing the file directly.

claude mcp add tradingview -- uvx --from /absolute/path/to/mcp-tradingview-server mcp-tradingview
5

Run the server

Start the MCP server in stdio mode (default for Claude Desktop) or as an HTTP/SSE service for other integrations.

# Default stdio mode:
uv run mcp-tradingview

# HTTP mode on port 8000:
uv run mcp-tradingview --transport http --host 0.0.0.0 --port 8000

TradingView Examples

Client configuration

Claude Desktop configuration using uvx to run the TradingView MCP server from the cloned repository path.

{
  "mcpServers": {
    "tradingview": {
      "command": "uvx",
      "args": ["--from", "/absolute/path/to/mcp-tradingview-server", "mcp-tradingview"],
      "env": {
        "FASTMCP_HOST": "127.0.0.1",
        "FASTMCP_PORT": "8000"
      }
    }
  }
}

Prompts to try

Example prompts for fetching TradingView indicators and market data through Claude.

- "Get all technical indicators for AAPL on the daily timeframe."
- "What is the RSI and MACD for BTC/USD on the 4-hour chart?"
- "Fetch the last 100 daily OHLCV candles for ETH/USD."
- "Get the moving averages (SMA 20, EMA 50) for TSLA on the 1-hour chart."
- "Analyze the Bollinger Bands for SPY on the weekly timeframe."
- "Export historical candlestick data for NVDA to a CSV file."

Troubleshooting TradingView

setup.sh fails with Python version error

Ensure Python 3.11 is installed and accessible. Run `python3.11 --version` to verify. If not installed, use pyenv (`pyenv install 3.11`) or download from python.org. Then re-run setup.sh.

get_indicators returns empty or null results for a symbol

Verify the symbol format matches TradingView conventions (e.g., NASDAQ:AAPL, BINANCE:BTCUSDT). Check that the exchange prefix is correct and the symbol is actively traded on TradingView.

Server starts but Claude Desktop does not list the tradingview tools

Confirm the absolute path in your config points to the correct repository directory. Restart Claude Desktop completely. Check the Claude Desktop logs for MCP server startup errors related to the uvx command.

Frequently Asked Questions about TradingView

What is TradingView?

TradingView is a Model Context Protocol (MCP) server that model context protocol (mcp) server that provides programmatic access to tradingview's technical indicators and market data for automated trading analysis and strategy development. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install TradingView?

Follow the installation instructions on the TradingView GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with TradingView?

TradingView works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is TradingView free to use?

Yes, TradingView is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Finance & Fintech MCP Servers

Explore all finance & fintech servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "mcp-tradingview": { "command": "npx", "args": ["-y", "mcp-tradingview"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use TradingView?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides