Atlas / MCP servers / mphinance / Momentum

MomentumSAFE

Name: Momentum
Author: mphinance

mcp/mphinance/momentum

MCP server by mphinance · Audited 2026-10-09

⚡ Give your AI agent a Bloomberg terminal. MCP server for stock screening, OHLCV data, technical analysis, chart generation, and financial news.

Verdict

SAFE

Grade

Trust score

89 /100

Exposed tools

73 66r · 7w · 0d

Transport

—

License

Apache-2.0

Stars

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

⚡ momentum-mcp

Give your AI agent a Bloomberg terminal.

A Model Context Protocol server for quantitative trading analysis.

Tools • Quickstart • Connect Your Client • Tech Stack • License

This toolkit shares its lineage with Vesper, a LangGraph trading agent for Webull — its mcp_server/ is a separate, credential-heavier superset (adds a live-account owner mode and, eventually, an order path). This repo stays the standalone version: point any MCP host at it, no broker anywhere near it. It's also part of the mphinance AI trading stack — if you want packaged Claude/Gemini Skills (screeners, regime detection, backtesting playbooks) that can call these tools instead of a paid API, see alpha-skills; if you want to act on what these tools tell you, see awesome-broker-mcp for which broker an AI can actually trade through.

Changelog

**September

Read from source at commit 44f1e4e632caOBSERVED · 2026-10-09

Exposed tools (73)

66 read · 7 write · 0 destructive.

Tool	Risk	Description
`analyze_breadth`	read	Get a comprehensive market breadth health score (0-100).
`analyze_options_setup`	read	VoPRTM engine: composite realized vol (4 estimators), VRP ratio,
`analyze_pair`	read	Analyze a pair of stocks for statistical arbitrage.
`analyze_recent_gap`	read	Score the most recent overnight gap reaction (0-100) for a specific ticker.
`analyze_scenario`	read	Generate bull/base/bear scenarios for a ticker based on a catalyst (e.g.
`analyze_technicals`	read	Compute 24 technical indicators: EMA 8/21/34/55/89, SMA 50/100/200,
`analyze_uptrend_participation`	read	Measure market participation in structural uptrends.
`backtest_strategy`	read	Backtest a trading strategy on historical data. 6 presets:
`calculate_position_size`	read	Calculate risk-based position size using Fixed Fractional, ATR, or Kelly methods.
`detect_bubble_risk`	read	Assess current market euphoria and bubble risk (0-15 score).
`detect_ftd`	read	Detect Follow-Through Days (FTDs) on major indices to confirm market bottoms.
`detect_macro_regime`	read	Detect the current structural market regime (Growth, Inflation, Deflation, or Goldilocks).
`detect_market_top`	read	Detect market topping signals using distribution days and leadership trends.
`detect_themes`	read	Identify trending market themes by clustering thematic ETF performance.
`etf_briefing`	read	Pre-market institutional briefing: top ETF buys and sells, multi-provider
`etf_divergences`	read	Cross-fund divergences: where different institutional funds traded the SAME
`etf_fund_detail`	read	One ETF
`etf_global_stats`	read	Coverage stats: funds tracked, unique underlyings, options contracts,
`etf_holdings_changes`	read	Raw institutional position changes, filterable by provider (
`etf_income_fund_detail`	read	One income fund
`etf_income_overview`	read	Option-income funds by structure: covered-call, synthetic, leap-proxy, swap.
`etf_institutional_flow`	read	Aggregate accumulation/distribution: all active-equity funds blended into
`etf_institutional_trend`	read	Per-ticker institutional accumulation/distribution trend across day, week
`etf_layering_patterns`	read	Layering: 3+ independent stock-pickers opening the SAME new position within
`etf_list_funds`	read	All 71 tracked funds with holdings counts and top positions.
`etf_list_tickers`	read	The most widely-held underlyings across all tracked funds (~2,270 total).
`etf_options_listings`	read	CBOE daily diff: newly optionable stocks and new weekly listings.
`etf_sector_flow`	read	Sector-level institutional inflows and outflows from fund holdings.
`etf_signal_performance`	read	Historical backtest performance of TickerTrace conviction signals.
`etf_signals`	read	Conviction-scored institutional buy/sell signals from daily ETF holdings
`etf_stock_activity`	read	Everything institutional for one stock: which funds hold it, how weights
`extract_article_text`	read	Extract the full-text body of a news article. Strips ads and nav.
`fetch_ticker_news`	read	Fetch recent financial news headlines for a stock from RSS feeds.
`find_best_to_buy`	read	Auto-find the best directional option to BUY. Reads technicals
`find_best_to_sell`	read	Auto-find the best puts and calls to SELL. Scans 7-45 DTE across
`generate_alpha_card`	read	Generate a shareable Alpha Card — a branded HTML analysis card.
`generate_chart`	read	Generate a candlestick chart with EMA overlays (8/21/34/55/89).
`get_alpha_signals`	read	Get recent alpha signals detected by the background signal factory.
`get_earnings_calendar`	read	Weekly earnings calendar — who reports this week.
`get_earnings_flow`	read	Pre-earnings options flow — institutional positioning ahead of earnings.
`get_exposure_recommendation`	read	Get a market exposure recommendation (0-100% capital deployment).
`get_fundamentals`	read	Get fundamental data: P/E, EPS, revenue growth, profit margin,
`get_gex_overview`	read	Gamma Exposure (GEX) for SPY/QQQ/IWM. Positive = pinning/calm.
`get_historical_data`	read	Fetch OHLCV historical price data for a stock.
`get_learned_patterns`	read	Get auto-extracted patterns from past backtests with win rates.
`get_market_environment`	read	Get a cross-asset market environment report.
`get_market_pulse`	read	AI-generated market sentiment with options flow score (-7 to +7).
`get_market_stats`	write	Market-wide put/call ratios and sentiment indicators.
`get_momentum_pulse`	read	Calculate real-time momentum scores (0-100) for each ticker.
`get_politician_trades`	read	Congressional stock trading disclosures.
`get_put_call_ratios`	write	Put/call ratios for SPY, QQQ, IWM (or any ticker).
`get_sec_filings`	read	SEC EDGAR filing index straight from the primary source: the
`get_sec_financials`	read	Multi-period financials from SEC XBRL, including the accrual gap
`get_sector_flow`	read	Sector-by-sector options flow with bullish/bearish sentiment.
`get_shares_outstanding`	read	Cover-page share count straight from the 10-Q/10-K filing, not an
`get_signals`	read	Breakout and continuation signals with technical indicator data.
`get_stakes_held`	read	AS-FILER 13D/13G: stakes this company holds in OTHER public companies
`get_track_record`	read	Get the full conviction journal track record with win/loss stats.
`get_tv_analysis`	read	Get TradingView 26-indicator technical consensus for a ticker.
`get_unusual_activity`	read	Unusual options flow feed — institutional trades, premium, conviction.
`list_strategies`	read	List all saved custom strategies.
`log_conviction`	read	Log a trade conviction to the journal. Direction: bullish/bearish/neutral.
`model_price_distribution`	read	Compute statistical price targets using historical volatility.
`run_custom_screen`	write	Build a custom stock screen with dynamic filter conditions.
`run_stock_screen`	write	Run a stock screen using TradingView
`save_strategy`	write	Save a custom strategy to disk for re-use.
`screen_canslim`	read	Screen for growth stocks matching CANSLIM criteria.
`screen_pead`	write	Screen for Post-Earnings Announcement Drift (PEAD) setups.
`screen_vcp`	read	Screen for stocks forming a Volatility Contraction Pattern (VCP).
`search_knowledge`	read	Search Sam
`sweep_setups`	read	Opportunity Board: scan multiple tickers for best options trades.
`sweep_strategy`	write	Run a strategy across multiple tickers (max 20). Ranks by Sharpe/return.
`walk_forward_test`	read	Walk-forward validation: splits data into n folds, detects overfitting.

Trust audit

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	PASS
L2	Instruction surface (what it tells the agent)	PASS
L3	Class-specific surface	PASS
L4	Behavioural (sandbox)	SKIPPED