Skip to main content
Glama
stockmarketscan/mcp-server

stockmarketscan/mcp-server

Official

StockMarketScan MCP Server

Stock screeners, chart patterns, options flow, and signals — 18 tools for US equities research, inside your LLM client.

  • Server URL: https://mcp.stockmarketscan.com/mcp

  • Transport: HTTP/SSE (Server-Sent Events)

  • Auth: BYOK — pass your personal sms_* API key as the X-API-Key header

  • Plan: Requires a Basic or Pro plan at stockmarketscan.com. Options flow tools require the Options Flow add-on.

  • Get your API key: stockmarketscan.com/settings

  • Full install guide & examples: stockmarketscan.com/mcp

What you get — 18 tools

Category

Tools

Screeners (3)

list_screeners, get_screener_data, search_stocks_in_screeners

Chart Patterns (2)

get_chart_patterns, search_patterns

Options Flow (4)

get_options_flow_overview, get_options_flow_timeline, get_options_flow_signals, get_unusual_options_activity

Stock Info (2)

get_stock_info, get_candles

Composite (2)

get_stock_report, search_setups

Market Context (3)

get_market_momentum, get_trends, get_trend_connections

Education (1)

explain_concept

Plus ping for liveness checks.

Related MCP server: Tickerbot MCP Server

Install — Claude Desktop

Edit claude_desktop_config.json:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "stockmarketscan": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.stockmarketscan.com/mcp"],
      "headers": {
        "X-API-Key": "sms_your_key_here"
      }
    }
  }
}

Restart Claude Desktop. You should see stockmarketscan in the tool picker.

Install — Cursor

Settings → Features → Model Context Protocol → Add New MCP Server:

{
  "name": "stockmarketscan",
  "url": "https://mcp.stockmarketscan.com/mcp",
  "headers": {
    "X-API-Key": "sms_your_key_here"
  }
}

Install — Continue (VS Code / JetBrains)

Edit ~/.continue/config.json:

{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "transport": {
          "type": "sse",
          "url": "https://mcp.stockmarketscan.com/mcp",
          "headers": {
            "X-API-Key": "sms_your_key_here"
          }
        }
      }
    ]
  }
}

Example prompts

Drop these straight into Claude Desktop or Cursor once the server is connected:

  • "Which stocks appear in both hot-prospects and golden-cross today?"

  • "Show me AMD's options flow history for the last 30 days."

  • "Find hot-prospects that are forming a cup and handle pattern."

  • "Build a full stock report for NVDA — screeners, patterns, options flow, market context."

  • "What are today's strongest bullish options flow signals?"

  • "Which contracts traded today at vol/OI > 3 with over $1M premium?"

How auth works (BYOK)

The MCP server does not hold its own API key. Each client passes your personal sms_* key, the server validates it once per session, and then proxies tool calls to api/v1/* on your behalf. You stay in control of rate limits and quota, and you can rotate the key any time in Settings.

Rate limits

Plan

Per Minute

Per Day

Options Flow

Free

—

—

—

Basic

15

500

—

Pro

30

2,000

✓

Support

Running from source

git clone https://github.com/stockmarketscan/mcp-server.git
cd mcp-server
npm install
STOCKMARKETSCAN_API_KEY=sms_your_key_here npm run dev   # stdio (for Claude Desktop local)
npm run dev:http                                        # HTTP/SSE on :3333

Docker

docker build -t stockmarketscan-mcp .
docker run -p 3333:3333 -e MCP_TRANSPORT=http stockmarketscan-mcp

The container listens on $PORT (Railway) or $MCP_PORT (local). Point your MCP client at http://localhost:3333/mcp and pass your X-API-Key header.

Available Tools

18 tools
explain_conceptA
Read-onlyIdempotent

Return a plain-language explanation of a platform-specific term, metric, or screener. Use ONLY for terms that are specific to StockMarketScan (e.g. 'strength_score' which is our internal scoring, or 'hot_prospects' which is our curated screener). Do NOT use for generic finance terms the model already knows — answer those directly. Returns { term, title, explanation, interpretation, related_terms }.

Inputs: term (required).

get_candlesA
Read-onlyIdempotent

Return OHLCV price candles for a single stock. Use when you need price history to compute indicators or answer 'how much is X up this month'. time is a Unix epoch in seconds (UTC midnight for daily). Default range is 6mo. Use larger ranges like '1y' or '2y' only when the user explicitly asks for long history — max range is 20 years. Returns { symbol, interval, range, count, data: [{time, open, high, low, close, volume}] }.

Inputs: symbol (required), interval, range.

get_chart_patternsA
Read-onlyIdempotent

Return all chart patterns currently detected for a single stock symbol. Covers 25+ patterns including head_shoulders, cup_handle, wedge_rising/falling, asc/desc/sym_triangle, double_top/bottom, channel_up/down, cup_handle, harmonic patterns (gartley, butterfly, bat, crab). Use when the user asks 'what patterns does X have' or 'is X forming a head and shoulders'. Returns { symbol, interval, computedAt, candleCount, patterns: [...] }. Empty patterns array if none detected.

Inputs: symbol (required), interval.

get_market_momentumA
Read-onlyIdempotent

Return NYSE and NASDAQ market breadth data — advancing/declining issues, new highs/lows, percent advancing. Use when the user asks 'how's the market today' or 'is breadth strong'. Default (no params): last 7 trading days. Returns { dates, count, data: [{exchange, advancing_issues, declining_issues, new_highs, new_lows, percent_advancing_issues, data_date}] }. Two rows per date (NYSE + NASDAQ). Tier: Basic+.

Inputs: date, date_from, date_to.

get_options_flow_overviewA
Read-onlyIdempotent

Return the daily options flow table for one trading day — aggregated call/put volume, premium, implied volatility, and consecutive-day streaks for every notable symbol. Use when the user asks 'what's the options flow today' or 'show me the top premium plays'. Each row includes call_put_volume_ratio (bullish if > 1.0), consecutive_days (streak length), total_premium (dollar size), call_avg_iv/put_avg_iv. Returns { date, sort, limit, data: [...], stats, dates }. Tier: Pro only — Basic users get 403.

Inputs: date, sort, limit.

get_options_flow_signalsA
Read-onlyIdempotent

Return curated high-conviction options flow signals for a date range. These are the strongest setups filtered by long streaks, large premium, and screener confluence. Each signal includes performance tracking (max_high_pct, max_drawdown_pct). Use when the user asks 'what are today's signals' or 'show me bullish setups from last week'. If date_from/date_to omitted, returns last 60 days. Returns { count, signals: [...] }. Tier: Pro only.

Inputs: date_from, date_to.

get_options_flow_timelineA
Read-onlyIdempotent

Return the historical options flow for a single stock — most recent days first. Use when the user asks 'show me X's options flow history' or 'how long has X been bullish'. Returns { symbol, limit, count, data: [daily rows, newest first] }. Tier: Pro only.

Inputs: symbol (required), limit.

get_screener_dataA
Read-onlyIdempotent

Return the current rows of a single stock screener for its latest data date. Use this when the user asks about a specific screener like 'hot prospects' or 'golden cross'. Common slugs: hot-prospects, golden-cross, death-cross, rsi-oversold, rsi-overbought, defensive-stocks, dividend-prospects, j-pattern, nearing-6-month-highs, week-52-high-top-picks, top-penny-pops, strong-volume-gains, top-tech-stocks, fundamentally-fine, income-and-growth, best-reits. If you don't know the slug, call list_screeners first. Returns { screener, pagination, data: [stock rows] }.

Inputs: slug (required), page, limit.

get_stock_infoA
Read-onlyIdempotent

Return basic metadata for a stock — full company name, exchange, industry, last close price, and percent change. Use this when you first encounter a symbol and need to identify it. Lighter than get_stock_report (composite) or get_candles (full history). Returns { symbol, symbol_name, last_price, percent_change, exchange, industry }. Returns NOT_FOUND for unknown tickers.

Inputs: symbol (required).

get_stock_reportA
Read-onlyIdempotent

Return a comprehensive report on a single stock in one call — metadata, screener appearances, chart patterns, options flow, signal status, price summary, and upcoming earnings. THIS IS THE PREFERRED FIRST TOOL when a user asks about a single stock. It replaces 5-7 separate tool calls (get_stock_info + get_chart_patterns + get_options_flow_timeline + get_options_flow_signals + screener lookups + get_candles). Do NOT also call the primitives after calling this — the composite already has everything. Parallel fetch under the hood, graceful partial failures (if one source errors, that section returns null with a note). Returns { symbol, info, screeners, patterns, options_flow, signal, candle_summary, upcoming_earnings, overall_bias }. overall_bias is a heuristic hint, not financial advice.

Inputs: symbol (required), interval.

get_trend_connectionsA
Read-onlyIdempotent

Return AI-computed connections between trending topics across categories (tech → patents, tech → funding, etc). Useful for spotting meta-trends. Use when the user asks 'what trends are connected' or 'show me cross-category signals'. Returns { count, connections: [{source_category, source_topic, target_category, target_topic, strength, rationale}] }. Tier: Pro only.

Inputs: days, latest, date.

get_unusual_options_activityA
Read-onlyIdempotent

Return individual options contracts flagged as unusual (Vol/OI > 1.5). Each row is one contract, not one stock. Use when the user wants contract-level detail. Filter by symbol, side (call/put/both), minimum vol/oi, minimum premium, or max days to expiration. For aggregated stock-level flow use get_options_flow_overview instead. Returns { date, count, contracts: [...] }.

Inputs: symbol, side, min_vol_oi, min_premium_usd, +2 more.

list_screenersA
Read-onlyIdempotent

Return metadata for all 24 stock screeners on the platform, including each screener's slug, name, description, category, and tier. Use this to discover which screeners are available before calling get_screener_data. Call this once per session — the list changes very rarely. Returns { tier, total, accessible, screeners: [...] }.

Inputs: no named parameters.

pingA
Read-onlyIdempotent

Minimal sanity check. Returns { status, version, timestamp, cache_size }. No auth needed. Use this to verify the MCP server is reachable and responsive.

Inputs: no named parameters.

search_patternsA
Read-onlyIdempotent

Find all stocks across one or more screeners that currently exhibit specific chart patterns. Much faster than calling get_chart_patterns in a loop. Use when the user asks 'which stocks have a cup and handle' or 'find me hot prospects with bullish reversal patterns'. Returns { screeners_queried, patterns_queried, interval, count, matches: [...] }.

Inputs: screener_slugs (required), pattern_ids, interval.

search_setupsA
Read-onlyIdempotent

Find the strongest trading setups today by combining options flow signals and screener confluence into a ranked list. Use when the user asks 'what should I trade today', 'best setups', 'top bullish plays'. Returns a ranked list with a composite score (signal strength + screener confluence + streak length). Present the top 3-5 to the user with narrative context, don't dump the raw JSON. Use get_stock_report if the user wants to dig deeper into any specific result. Returns { side, date, count, setups: [{symbol, score, signal, screeners_hit, ...}] }.

Inputs: side, limit.

search_stocks_in_screenersA
Read-onlyIdempotent

Find stocks that appear in multiple screeners simultaneously. Powerful for high-confidence picks where the user wants confluence across strategies. Use when the user asks 'which stocks are in both X and Y' or 'find stocks in 3+ bullish screeners'. Returns { screeners_queried, mode, count, symbols: [{symbol, screeners, match_count}] }. Intersection mode returns only stocks in ALL listed screeners; union returns stocks in ANY.

Inputs: screener_slugs (required), mode, limit.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.4/5.0

    Scored across 18 tools

    Disambiguation5/5

    Each tool targets a distinct resource or action. Even closely related tools like options flow variants (overview vs signals vs timeline vs unusual activity) have clear differentiating descriptions. The search tools (search_patterns, search_setups, search_stocks_in_screeners) are well-separated from lookup tools.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern with snake_case: get_*, search_*, list_*, explain_, ping. There is no mixing of styles or unclear verb usage.

    Tool Count5/5

    18 tools is appropriate for a comprehensive stock scanning platform. The tool count covers all major dimensions (info, candles, patterns, screeners, options, trends) without feeling bloated or sparse.

    Completeness5/5

    The tool surface is remarkably complete for the domain. It provides CRUD-like operations (retrieve, search, explain) for each concept, and the composite get_stock_report consolidates many primitives. There are no obvious gaps for typical stock analysis tasks.

    Maintenance

    ActivityInactive
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      A modular MCP server providing 64 tools across 13 modules for real-time stock and crypto market data, including scanning, technical analysis, options flow, insider trades, and personalized watchlists.
      39
      199 npm
      8
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables scanning and querying stock market data across thousands of US tickers and top cryptos, with tools for signal analysis, historical replay, and webhook subscriptions.
      35
      583 npm
      MIT
    • A
      license
      C
      quality
      D
      maintenance
      An MCP server for stock research with 52 tools across FMP and Qualtrim backends, providing raw financial data plus derived analytics, DCF, AI commentary, and portfolio management. It handles caching, API budgeting, and credential management.
      33
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables MCP-based access to a US stock data warehouse and screener, allowing automated screening with daily free market data.
      MIT