Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
6,000+ web scrapers for your AI agent, start free logo6,000+ web scrapers for your AI agent, start free

Apify gives your agent live web data: 6,000+ prebuilt scrapers and actors, MCP-ready. Sign up free with $5 in usage credits.

Try Apify free
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 48,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Works with

Claude CodeClaude DesktopCursorVS CodeClineCodex CLIOpenClaw+ any MCP client

Install to Claude Code

This server doesn't publish a one-line install command. Follow the setup in the source repository.

Summary

Provides TradingView-style market analysis with OHLCV candles, 19 technical indicators, a screener, and a backtester using public Yahoo Finance data without API keys.

README.md

TradingView MCP Server

A community Model Context Protocol server that gives Claude Code (or any MCP client) TradingView-style market analysis: OHLCV candles, a suite of 19 technical indicators, a flexible technical screener, and a simple backtester.

Data is pulled from public Yahoo Finance endpoints — no API key, no account, no session cookies. Low blast radius: it only performs read-only fetches of public market data.

⚠️ Not affiliated with TradingView. Programmatic market-data collection can conflict with a provider's Terms of Use. This server avoids touching any TradingView account directly, but use it at your own discretion. Nothing here is financial advice.

Features

| Tool | What it does | | --- | --- | | get_price | Latest snapshot: price, day range, volume, market cap, % change. | | get_candles | OHLCV candles for any interval/period. | | list_indicators | Lists every indicator the server can compute. | | get_indicators | Computes one or more indicators (with custom params). | | screen_symbols | Screens a list of tickers against technical conditions. | | backtest | Long-only SMA-crossover backtest vs. buy & hold. | | list_market_options | Valid intervals, periods, and ticker formats. |

Indicators: SMA, EMA, WMA, HMA, RSI, ROC, momentum, MACD, Bollinger Bands, Stochastic, Williams %R, CCI, ATR, Keltner Channels, Donchian Channels, ADX, OBV, VWAP, MFI.

Tickers follow Yahoo conventions: stocks AAPL, crypto BTC-USD, forex EURUSD=X, indices ^GSPC.

Install

# 1. Install uv if you don't have it
curl -LsSf https://astral.sh/uv/install.sh | sh

# 2. Register the server with Claude Code (runs straight from this repo)
claude mcp add tradingview -- uvx --from /path/to/Trading-view-MCP tradingview-mcp

To make it available in every project (user scope) rather than just the current one:

claude mcp add -s user tradingview -- uvx --from /path/to/Trading-view-MCP tradingview-mcp

Once published to PyPI you'd instead use:

uv tool install tradingview-mcp-server
claude mcp add tradingview -- uvx --from tradingview-mcp-server tradingview-mcp

Verify

claude mcp list      # tradingview should show "connected"

Inside a session, /mcp lists the live tools. Then just ask in plain language, e.g. "screen AAPL, MSFT, NVDA for RSI under 35 on the daily" — Claude calls the tools itself.

📱 Mobile bias web app

A one-button mobile web app that runs the multi-timeframe bias (15m, 1h, 4h, daily, weekly) and prints Bullish / Bearish / Neutral for each, plus an overall verdict.

uv run --extra web uvicorn webapp.app:app --host 0.0.0.0 --port 8000

Then open http://<your-computer-ip>:8000 on your phone (same Wi-Fi), or http://localhost:8000 on the same machine. Type a ticker (defaults to GC=F, gold ≈ XAUUSD), tap Run Analysis, and you get a colour-coded board.

The same logic is exposed to Claude as the get_bias MCP tool, so you can also just ask "what's the bias on gold across timeframes?".

Caching

Results are cached two ways so repeated taps don't hammer Yahoo:

  • Edge/CDN cache (in production): responses carry

Cache-Control: s-maxage=60, stale-while-revalidate=300, so repeat requests within 60s are served from Vercel's edge without invoking the function.

  • In-process TTL cache: a 60s thread-safe cache (warm instances + local dev

+ the MCP tool). Override the window with the BIAS_CACHE_TTL env var.

Each response includes a cached flag, and the page shows cached ⚡ vs live.

How the bias is scored

Each timeframe casts 7 votes (price vs EMA20/EMA50, EMA20 vs EMA50, MACD histogram, RSI, ADX direction, Stochastic). Score ≥ +2 → Bullish, ≤ −2 → Bearish, otherwise Neutral. It's a transparent tally, not a black box — and it is not financial advice.

Run it directly

uv run tradingview-mcp            # starts the stdio server

Tool examples

Screen for oversold names below their 200-day average:

{
  "symbols": ["AAPL", "MSFT", "NVDA", "TSLA"],
  "conditions": [
    {"indicator": "rsi", "params": {"length": 14}, "op": "<", "value": 35},
    {"indicator": "close", "op": "<",
     "value": {"indicator": "sma", "params": {"length": 200}}}
  ],
  "match": "all"
}

Detect a 20/50 EMA bullish crossover:

{
  "symbols": ["BTC-USD", "ETH-USD"],
  "conditions": [
    {"indicator": "ema", "params": {"length": 20}, "op": "crosses_above",
     "indicator2": "ema", "params2": {"length": 50}}
  ]
}

Multi-column indicators (macd, bollinger, stochastic, adx, keltner, donchian) take a column, e.g. {"indicator": "macd", "column": "histogram", "op": ">", "value": 0}.

Development

uv sync --extra dev
uv run pytest          # indicator + screener tests, no network needed

Architecture

src/tradingview_mcp/
  server.py       # FastMCP tool definitions (the MCP surface)
  data.py         # the only module that touches the network (yfinance)
  indicators.py   # pure pandas/numpy indicator engine (TA-Lib-free)
  screener.py     # screening + backtesting on top of the engine

License

MIT

See related servers & alternatives →

Related MCP servers

Browse all →

Related guides

Hand-picked reading to help you choose and use Finance & Payments servers.