# us-stock-etf-quant-signal-mcp (`mcp_collector/us-stock-etf-quant-signal-mcp`) Actor Ultra-fast (<5s) MCP tool for AI agents. Computes Wilder's RSI(14) turnaround, MFI(14), Bollinger %B, MA20/MA200 reclaim status, MACD histogram, RVOL, 2x ATR stop-loss, and Dip vs. Rebound scores (0-100) in compact JSON/Markdown. - **URL**: https://apify.com/mcp_collector/us-stock-etf-quant-signal-mcp.md - **Developed by:** [koon](https://apify.com/mcp_collector) (community) - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks - **User rating**: No ratings yet ## Pricing $8.00 / 1,000 stock & etf quant signal generateds This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event ## What's an Apify Actor? An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md. ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run. For examples already wired to this Actor's own input schema, see the [API](#api) section below. Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`). # README ## 📈 US Stock & ETF Quant Technical Signals MCP (RSI, MFI, MACD, 2x ATR Stop-Loss) **Built specifically for AI Agents (Claude, Cursor, ChatGPT, LangChain) and Quantitative Workflows.**\ Stop feeding thousands of raw OHLCV candle rows into your LLM context window. This lightweight Actor fetches 1-year daily market data and returns **pre-calculated, institutional-grade technical indicators, turnaround signals, and risk-management stop-loss levels** in **under 5 seconds** (~1KB per ticker). *** ### 🤖 Why AI Agents & Developers Choose This Tool over Raw Scrapers 1. **95% Token & Context Saving (MCP-Ready)**: Raw Yahoo Finance scrapers dump 250+ rows of uncalculated OHLCV numbers per ticker, overflowing LLM context windows and causing math hallucinations. This tool delivers exact, deterministic metrics ready for immediate reasoning. 2. **Falling Knife vs. Confirmed Rebound Detection (2-Track Scoring)**: - **`dip_buy_score` (0–100)**: Measures valuation & oversold depth using Wilder's RSI(14), Money Flow Index (MFI 14), and Bollinger Band `%B`. - **`rebound_confirm_score` (0–100)**: Detects actual bullish turnarounds by checking **RSI turn-up (`rsi_delta > 0`)**, **20-day MA reclaim (`JUST_RECLAIMED_MA20`)**, **MACD histogram expansion**, and **Relative Volume (`rvol_20d >= 1.2x`)**. 3. **Timestamp Integrity**: Every output includes exact `market_time_utc` (regular market close/trade timestamp) and `analyzed_at_kst` so AI agents never confuse weekend/after-hours runs with live intraday prices. 4. **Built-in Risk Management (`suggested_stop_loss_2atr`)**: Automatically computes 14-day Wilder's Average True Range (ATR) and provides a scientific `2x ATR` trailing stop-loss price. *** ### 📊 Output Data Fields (JSON & Markdown Summary) For each requested ticker, the Actor pushes a structured item to the Dataset: | Field | Type | Description | | :--- | :--- | :--- | | `ticker` | `string` | Uppercase symbol (e.g., `NVDA`, `SPY`, `SOXX`) | | `market_time_utc` | `string` | Exact market data timestamp in UTC (e.g., `2026-10-16 20:00:00 UTC`) | | `last_price` | `number` | Latest closing / market price ($) | | `action_signal` | `string` | Deterministic verdict: `CONFIRMED_REBOUND_BUY`, `OVERSOLD_WATCH_WAIT_TURN`, `MOMENTUM_BREAKOUT_BUY`, `OVERBOUGHT_TRIM_OR_HOLD`, or `NEUTRAL_HOLD` | | `dip_buy_score` | `number` | 0–100 score indicating oversold depth (higher = cheaper/more oversold) | | `rebound_confirm_score` | `number` | 0–100 score confirming bullish momentum turn-up (higher = stronger rebound) | | `rsi_14` / `rsi_prev` / `rsi_delta` | `number` | Wilder's 14-day RSI today, yesterday, and daily change ($\Delta$) | | `rsi_rebound_status` | `string` | Turnaround state (e.g., `TURN_UP_IN_BUY_ZONE`, `OVERSOLD_FALLING`) | | `ma20_diff_pct` / `ma20_status` | `number` / `string` | Distance (%) from 20-day SMA and reclaim status (`JUST_RECLAIMED_MA20`, `HOLDING_ABOVE_MA20`, `BELOW_MA20_RESISTANCE`) | | `ma200_diff_pct` | `number` | Distance (%) from 200-day SMA (long-term trend filter) | | `mfi_14` | `number` | 14-day Volume-weighted Money Flow Index (0–100) | | `bb_pct_b` | `number` | Bollinger Bands (20, 2) `%B` position (`< 0` below lower band, `> 1` above upper band) | | `macd_hist` / `macd_status` | `number` / `string` | MACD(12,26,9) histogram value and momentum crossover status | | `rvol_20d` | `number` | Relative Volume ratio compared to 20-day average volume (e.g., `1.82` = 182% volume) | | `drawdown_52w_pct` | `number` | Percentage drawdown from 52-week high | | `atr_14` / `atr_pct` | `number` | 14-day Wilder's Average True Range ($) and volatility percentage (%) | | `suggested_stop_loss_2atr` | `number` | Recommended volatility-adjusted stop-loss price ($\text{Last Price} - 2 \times \text{ATR}$) | | `summary_md` | `string` | One-line pre-formatted Markdown brief ready for direct LLM output | *** ### 💻 Sample Output (`JSON`) ````json { "ticker": "NVDA", "market_time_utc": "2026-10-16 20:00:00 UTC", "last_price": 214.13, "action_signal": "NEUTRAL_HOLD", "dip_buy_score": 69.0, "rebound_confirm_score": 0.0, "rsi_14": 37.53, "rsi_prev": 40.17, "rsi_delta": -2.64, "rsi_rebound_status": "NEUTRAL_FLOW (Δ-2.64)", "ma20_diff_pct": -6.16, "ma20_status": "BELOW_MA20_RESISTANCE", "ma200_diff_pct": 5.5, "mfi_14": 28.4, "bb_pct_b": 0.11, "macd_hist": -2.357, "macd_status": "BEARISH_MOMENTUM", "rvol_20d": 1.15, "drawdown_52w_pct": -14.2, "atr_14": 5.97, "atr_pct": 2.79, "suggested_stop_loss_2atr": 202.19 } # Actor input Schema ## `tickers` (type: `array`): List of US Stock or ETF ticker symbols to analyze (e.g., ["NVDA", "TSLA", "AAPL", "SPY", "QQQ", "SOXX"]). ## `maxItems` (type: `integer`): Maximum number of tickers to process in a single call to control Pay-Per-Event budget. ## Actor input object example ```json { "tickers": [ "SPY", "QQQ", "SOXX", "NVDA", "TSLA" ], "maxItems": 50 } ```` # Actor output Schema ## `results` (type: `string`): No description # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "tickers": [ "SPY", "QQQ", "SOXX", "NVDA", "TSLA" ] }; // Run the Actor and wait for it to finish const run = await client.actor("mcp_collector/us-stock-etf-quant-signal-mcp").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "tickers": [ "SPY", "QQQ", "SOXX", "NVDA", "TSLA", ] } # Run the Actor and wait for it to finish run = client.actor("mcp_collector/us-stock-etf-quant-signal-mcp").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}") for item in client.dataset(run.default_dataset_id).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash echo '{ "tickers": [ "SPY", "QQQ", "SOXX", "NVDA", "TSLA" ] }' | apify call mcp_collector/us-stock-etf-quant-signal-mcp --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "type": "http", "url": "https://mcp.apify.com/?tools=fetch-actor-details,mcp_collector/us-stock-etf-quant-signal-mcp" } } } ``` The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer ` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations). ## OpenAPI specification Download the OpenAPI definition: https://api.apify.com/v2/actors/ILduuDa5OPtdzgpOb/builds/JvHw9kMthAGdejgy9/openapi.json