mcpField
S
stock-performance

stock-performance

github.com/octagonaiData & databases130260 installsUpdated 21w ago
Repository

About stock-performance

This skill retrieves daily prices, trading volume, and performance metrics for public companies through Octagon MCP. It is intended for investors and traders analyzing selected stocks and periods, and also supports comparisons across multiple stocks.

Key features

  1. 01Retrieve daily closing prices and volume
  2. 02Query opening, high, and low prices
  3. 03Review historical prices by date range
  4. 04Compare performance across multiple stocks

Use cases

  1. 01Analyze recent price and volume trends
  2. 02Track portfolio performance
  3. 03Assess the impact of earnings or news
  4. 04Compare relative performance among peers

MCP support

Requires Octagon MCP configured in an AI agent and uses the octagon-agent tool to query stock performance data.

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/octagonai/skills --skill stock-performance

After installing, type/stock-performancein Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

marketplace.json
README.md
references/
interpreting-results.md
mcp-setup.md

Details

From the project README

Stock Performance

Retrieve daily closing prices, trading volume, and performance metrics for public companies using the Octagon MCP server.

Prerequisites

Ensure Octagon MCP is configured in your AI agent (Cursor, Claude Desktop, Windsurf, etc.). See references/mcp-setup.md for installation instructions.

Workflow

1. Identify Analysis Parameters

Determine the following before querying:

  • Ticker: Stock symbol (e.g., AAPL, MSFT, GOOGL)
  • Time Period: Number of days or date range
  • Metrics (optional): Price, volume, returns
2. Execute Query via Octagon MCP

Use the octagon-agent tool with a natural language prompt:

Retrieve the daily closing prices for <TICKER> over the last <N> days.

MCP Call Format:

{
  "server": "octagon-mcp",
  "toolName": "octagon-agent",
  "arguments": {
    "prompt": "Retrieve the daily closing prices for AAPL over the last 30 days."
  }
}
3. Expected Output

The agent returns structured price data including:

DateClosing PriceVolume
2026-02-02$270.0173,677,607
2026-01-30$259.4892,443,408
2026-01-29$258.2867,253,009
.........

Data Sources: octagon-stock-data-agent, octagon-web-search-agent

4. Interpret Results

See references/interpreting-results.md for guidance on:

  • Analyzing price trends
  • Evaluating volume patterns
  • Calculating returns
  • Identifying support/resistance levels

Example Queries

Daily Closing Prices:

Retrieve the daily closing prices for AAPL over the last 30 days.

Extended Historical Data:

Get historical stock prices for MSFT for the past 90 days.

Volume Analysis:

Retrieve daily trading volume for TSLA over the last 2 weeks.

Price Range:

What are the high and low prices for NVDA over the past month?

Multi-Stock Comparison:

Compare the stock performance of AAPL, MSFT, and GOOGL over the last 30 days.

52-Week Analysis:

What is the 52-week high and low for AMZN?

Key Metrics

Price Metrics
MetricDescription
Closing PriceEnd-of-day price
Opening PriceStart-of-day price
HighIntraday high
LowIntraday low
Adjusted CloseDividend/split adjusted
Volume Metrics
MetricDescription
Daily VolumeShares traded per day
Average VolumeTypical daily volume
Relative VolumeCurrent vs. average
Volume TrendDirection over time
Return Metrics
MetricCalculation
Daily Return(Close - Prior Close) / Prior Close
Period Return(End - Start) / Start
Cumulative ReturnRunning return over period
Annualized ReturnPeriod return scaled to 1 year

Price Analysis Framework

Trend Analysis
PatternCharacteristics
UptrendHigher highs, higher lows
DowntrendLower highs, lower lows
SidewaysRange-bound movement
BreakoutMove beyond range
Volatility Assessment
MeasureDescription
Price RangeHigh - Low over period
Daily RangeAverage daily high-low
Standard DeviationPrice dispersion
BetaRelative to market
Support/Resistance
LevelDescription
SupportPrice floor, buying interest
ResistancePrice ceiling, selling pressure
Moving AveragesDynamic support/resistance
Round NumbersPsychological levels

Volume Analysis

Volume Patterns
PatternInterpretation
High Volume + Price UpStrong buying conviction
High Volume + Price DownStrong selling pressure
Low Volume + Price UpWeak rally, may reverse
Low Volume + Price DownLack of selling interest
Volume Indicators
IndicatorUsage
Volume SpikeUnusual activity, potential catalyst
Volume Dry-upConsolidation, waiting mode
Volume TrendConfirms price trend
On-Balance VolumeCumulative volume direction

Time Period Analysis

Short-Term (1-30 Days)
FocusUse Case
Recent PerformanceCurrent momentum
Trading SignalsEntry/exit timing
News ImpactEvent analysis
VolatilityRisk assessment
Medium-Term (1-6 Months)
FocusUse Case
Trend IdentificationDirection confirmation
SeasonalityCyclical patterns
Earnings ImpactQuarterly effects
Sector RotationRelative performance
Long-Term (1+ Years)
FocusUse Case
Major TrendsSecular moves
52-Week RangeValuation context
Recovery/DeclineMajor shifts
Dividend YieldIncome analysis

Comparative Analysis

Peer Comparison
MetricWhat to Compare
ReturnRelative performance
VolatilityRisk comparison
CorrelationMovement similarity
VolumeLiquidity comparison
Benchmark Comparison
BenchmarkUsage
S&P 500Large cap reference
Sector ETFIndustry context
NasdaqTech comparison
Russell 2000Small cap reference

Analysis Tips

  1. Consider context: Market conditions affect individual stocks.

  2. Adjust for events: Earnings, dividends, splits affect prices.

  3. Use volume confirmation: Price moves need volume support.

  4. Multiple timeframes: Longer and shorter perspectives.

  5. Compare to peers: Relative performance matters.

  6. Watch key levels: Round numbers, 52-week highs/lows.

Use Cases

  • Trading analysis: Entry and exit timing
  • Performance tracking: Portfolio monitoring
  • Event analysis: Earnings, news impact
  • Volatility assessment: Risk evaluation
  • Peer comparison: Relative performance

Comments

Markdown supported