Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Query TradingView market data through the bundled tradingview MCP server without a desktop app or login. Use whenever the user wants a technical analysis readout (RSI, MACD, Bollinger rating, BUY/SELL summary), multi-timeframe alignment (weekly→daily→4h→1h→15m), exchange-wide scans (Bollinger squeeze, volume breakout, consecutive candles, smart volume), top gainers/losers by exchange, futures market data (NQ/ES/CL/GC overview, overnight movers, category snapshots), pre-market / after-hours quote
.claude/skills/himself65-tradingview-mcp/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 7% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 466% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -3% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 68% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 73% | 0% |
Market data via the bundled tradingview MCP server — TradingView's public scanner API plus Yahoo Finance, spoken over MCP. No TradingView desktop app or account. Most tools need no API key. The server ships with this plugin (.mcp.json) and starts automatically; its 37 tools appear under the plugin's tradingview MCP namespace (load them through the client's deferred-tool mechanism when necessary).
Read-only. Nothing here places trades or mutates any account.
| Need | Skill | |---|---| | Quotes, TA readout, indicator ratings, multi-timeframe alignment | this skill | | Exchange-wide scans: squeeze / volume breakout / gainers / losers | this skill | | Futures (NQ, ES, CL, GC…) overview, movers, category quotes | this skill | | Pre-market / after-hours price | this skill | | Options chain quick look (bid/ask/IV/OI, no greeks), unusual activity | this skill (fallback / positioning scan) | | Options chain with greeks (delta/gamma/theta/vega), IV skew, expiries with contract counts | tradingview-reader (desktop app) | | Watchlists, alerts, TV news, chart state / screenshots, custom-column screener | tradingview-reader (desktop app) |
Rule of thumb: this skill first for anything price/TA/scan shaped — it needs zero setup and won't force a CDP relaunch of the user's TradingView app. Drop to tradingview-reader only for greeks or account-bound data (watchlists, alerts, charts).
uv installed (brew install uv) — the server runs via uvx and self-installs on first launch (give the first call ~30s).MARKETAUX_API_TOKEN enables market_sentiment, financial_news, and the news legs of combined analysis.If the MCP tools are missing, ask the user to restart the agent after enabling the plugin. Do not silently replace market data with invented values.
Prefer one focused call for a simple question. For a research brief, combine only the independent views that matter: price/snapshot, TA, volume, and optionally news. Avoid calling multiple overlapping TA tools merely to produce more output.
| Tool | Use for | |---|---| | stock_prices(tickers) | Bulk quotes. tickers is comma-separated EXCHANGE:SYMBOL (e.g. "NASDAQ:NVDA,NYSE:DELL"), up to 1,000 rows in one call. OHLC + change%. | | yahoo_price(symbol) | Single quote, Yahoo symbology: AAPL, BTC-USD, SPY, ^GSPC, ^VIX, EURUSD=X, THYAO.IS. | | stock_extended_hours(symbol) | Pre-market / after-hours price for a US symbol — earnings reactions, overnight moves. | | market_snapshot() | Global one-shot: major indices, top crypto, FX, key ETFs. | | bitcoin_market_pulse() | BTC price + dominance + total mcap risk frame — call before analyzing any crypto. |
| Tool | Use for | |---|---| | coin_analysis(symbol, exchange, timeframe) | The canonical TA readout for one stock or coin — RSI, MACD, Bollinger rating, indicator summary. Despite the name it handles stocks: coin_analysis("NVDA", "NASDAQ", "1D"). | | multi_timeframe_analysis(symbol, exchange) | Weekly → Daily → 4H → 1H → 15m trend alignment. | | combined_analysis(symbol, exchange, timeframe) | TA + news + sentiment in one call (news legs need MARKETAUX_API_TOKEN). | | multi_agent_analysis(symbol, exchange, timeframe) | Technical vs Sentiment vs Risk "debate" summary. | | volume_confirmation_analysis(symbol, exchange, timeframe) | Is the move volume-confirmed? |
| Tool | Use for | |---|---| | top_gainers / top_losers(exchange, timeframe, limit) | Movers on one exchange. | | bollinger_scan(exchange, timeframe, bbw_threshold, limit) | Low-BBW squeeze candidates. | | rating_filter(exchange, timeframe, rating, limit) | Filter by BB rating −3 (strong sell) … +3 (strong buy). | | volume_breakout_scanner / smart_volume_scanner | Volume + price breakout detection. | | consecutive_candles_scan / advanced_candle_pattern | Candle-pattern scans. | | stock_screener(country, stock_type, limit, …) | Common/preferred share screen by country (america, japan, …), mcap-ranked. |
| Tool | Use for | |---|---| | futures_market_overview(category, exchanges, limit) | Top contracts by volume. category: all / equity_index / energy / metals / agriculture / rates / forex / crypto_futures; exchanges: us / global. | | futures_top_movers(direction, exchanges, limit) | Biggest % movers today. | | futures_category_snapshot(category) | OHLCV for all front-month contracts in one category — e.g. equity_index → NQ, ES, YM, RTY. | | futures_watchlist() | Canonical front-month symbol list per category. |
| Tool | Use for | |---|---| | stock_options_chain(symbol, expiry) | Calls + puts for one expiry (YYYY-MM-DD; omit → nearest). Returns strike, last, bid/ask, volume, OI, IV, ITM flag, plus the full available_expiries list. Source: Yahoo. No delta/gamma/theta/vega — use tradingview-reader for greeks. | | stock_options_unusual_activity(symbol, top_n, min_volume, expiries) | Top strikes by volume/OI ratio across the soonest expiries — positioning scan before earnings. |
| Tool | Use for | |---|---| | backtest_strategy(symbol, strategy, period, interval, …) | One strategy (rsi, bollinger, macd, ema_cross, supertrend, donchian, rsi_pullback, keltner_breakout, triple_ema) with Sharpe, max DD, win rate, vs buy-and-hold. Yahoo symbology. | | compare_strategies(symbol, period, …) | All 9 strategies ranked. | | walk_forward_backtest_strategy(…) | Train/test split with an overfitting verdict. |
MARKETAUX_API_TOKEN)market_sentiment(symbol, category) · financial_news(symbol, category, limit)
egx_* (Egyptian Exchange suite) — rarely relevant; also BIST, HKEX, SSE, SZSE, TWSE supported via the exchange param on scan tools.
exchange defaults to KUCOIN (crypto!) on most scan/TA tools — always pass NASDAQ / NYSE explicitly for US equities.exchange param; stock_prices takes EXCHANGE:SYMBOL; Yahoo-backed tools (yahoo_price, backtests, options) take Yahoo tickers (BTC-USD, ^VIX, THYAO.IS).5m, 15m, 1h, 4h, 1D, 1W, 1M. Intraday scans on stock exchanges can be sparse — prefer 1D for equities.coin_analysis and multi_timeframe_analysis, not README-style aliases such as get_technical_analysis.tradingview-reader.Lead with the answer, then show a compact evidence table. Include an as-of timestamp and data source, name any missing or stale fields, and separate observed facts from interpretation. For trading-shaped requests, keep the response analytical and read-only: discuss risks and scenarios without placing or offering to place a trade.
The server is pinned to an immutable upstream commit in .mcp.json. To upgrade it, select a reviewed SHA, update the pin, perform a real MCP initialize + tools/list handshake, confirm all tools remain read-only, and reconcile this catalog with the registered tool names and schemas.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 20,089 | 11,844 | -41% | 1 | 1 | 0% | 2,668 | 2,697 | +1% | 0 | 0 | — |
case-02 | fail→fail | 21,404 | 15,139 | -29% | 1 | 1 | 0% | 3,256 | 2,628 | -19% | 0 | 0 | — |
case-03 | fail→fail | 24,240 | 16,675 | -31% | 1 | 1 | 0% | 3,473 | 2,625 | -24% | 0 | 0 | — |
case-04 | fail→pass | 21,778 | 10,759 | -51% | 1 | 1 | 0% | 2,997 | 3,198 | +7% | 0 | 0 | — |
case-05 | fail→pass | 8,252 | 8,366 | +1% | 1 | 1 | 0% | 489 | 2,767 | +466% | 0 | 0 | — |
case-06 | fail→fail | 9,996 | 19,041 | +90% | 1 | 1 | 0% | 853 | 2,948 | +246% | 0 | 0 | — |
case-15 | fail→pass | 22,125 | 7,424 | -66% | 1 | 1 | 0% | 2,856 | 2,782 | -3% | 0 | 0 | — |
case-07 | fail→pass | 15,327 | 7,681 | -50% | 1 | 1 | 0% | 1,610 | 2,700 | +68% | 0 | 0 | — |
case-08 | fail→pass | 14,950 | 8,756 | -41% | 1 | 1 | 0% | 1,750 | 3,033 | +73% | 0 | 0 | — |
case-09 | fail→pass | 17,173 | 8,815 | -49% | 1 | 1 | 0% | 1,911 | 2,876 | +50% | 0 | 0 | — |
case-10 | fail→pass | 11,448 | 8,239 | -28% | 1 | 1 | 0% | 1,191 | 2,819 | +137% | 0 | 0 | — |
case-16 | fail→pass | 17,772 | 7,677 | -57% | 1 | 1 | 0% | 2,216 | 2,748 | +24% | 0 | 0 | — |
case-11 | fail→pass | 16,496 | 19,111 | +16% | 1 | 1 | 0% | 2,149 | 3,188 | +48% | 0 | 0 | — |
case-12 | fail→fail | 18,215 | 16,322 | -10% | 1 | 1 | 0% | 2,193 | 2,648 | +21% | 0 | 0 | — |
case-13 | fail→pass | 19,710 | 8,040 | -59% | 1 | 1 | 0% | 2,252 | 2,680 | +19% | 0 | 0 | — |
case-14 | fail→pass | 19,566 | 7,792 | -60% | 1 | 1 | 0% | 2,172 | 2,793 | +29% | 0 | 0 | — |
case-17 | pass→pass | 18,918 | 8,307 | -56% | 1 | 1 | 0% | 2,096 | 2,843 | +36% | 0 | 0 | — |
case-18 | fail→pass | 12,768 | 7,636 | -40% | 1 | 1 | 0% | 1,466 | 2,681 | +83% | 0 | 0 | — |
case-19 | fail→pass | 20,930 | 8,396 | -60% | 1 | 1 | 0% | 2,401 | 2,869 | +19% | 0 | 0 | — |
case-20 | fail→pass | 17,251 | 7,775 | -55% | 1 | 1 | 0% | 2,110 | 2,699 | +28% | 0 | 0 | — |
case-26 | fail→pass | 17,601 | 7,398 | -58% | 1 | 1 | 0% | 2,032 | 2,638 | +30% | 0 | 0 | — |
case-21 | fail→pass | 20,567 | 7,417 | -64% | 1 | 1 | 0% | 2,461 | 2,695 | +10% | 0 | 0 | — |
case-22 | pass→pass | 11,774 | 7,289 | -38% | 1 | 1 | 0% | 1,104 | 2,603 | +136% | 0 | 0 | — |
case-23 | fail→pass | 18,994 | 9,970 | -48% | 1 | 1 | 0% | 2,387 | 3,105 | +30% | 0 | 0 | — |
case-24 | pass→pass | 17,630 | 7,623 | -57% | 1 | 1 | 0% | 2,170 | 2,723 | +25% | 0 | 0 | — |
case-25 | fail→pass | 15,937 | 10,222 | -36% | 1 | 1 | 0% | 1,890 | 3,138 | +66% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 26 cases were attempted, and 21 counted toward the lift figure. The other 5 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +69 percentage points is the difference between those two pass rates over the 21 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.