Skip to main content
Glama
grahammccain

Chart Library

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CHART_LIBRARY_API_KEYNoOptional API key for higher rate limits

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
search_chartsA

Search for historically similar chart patterns.

Input a symbol and date (e.g. 'AAPL 2024-06-15') to find the top 10
most similar historical charts from 800M+ minute bars.
Results include match scores and similarity distances.

Args:
    query: Symbol + date, e.g. 'AAPL 2024-06-15' or 'TSLA 6/15/24 3d'
    timeframe: Session: rth (regular hours), premarket, rth_3d, rth_5d, or auto
    top_n: Number of results (1-50)
get_follow_throughA

Get forward return analysis for search results.

Pass the results from search_charts to see what happened 1, 3, 5, and 10
days later in each historical match. Returns % returns and cumulative paths.

Args:
    results: Search results from search_charts (list of {symbol, date, timeframe, metadata})
get_pattern_summaryB

Generate an AI-written plain English summary of pattern search results.

Returns a concise 2-3 sentence summary suitable for retail traders.

Args:
    query_label: Human-readable query label (e.g. 'AAPL 2024-06-15')
    n_matches: Number of matches found
    horizon_returns: Forward returns dict {1: [...], 3: [...], 5: [...], 10: [...]}
get_statusA

Get Chart Library database statistics.

Returns total embeddings, coverage percentage, date range, and distinct symbols.

analyze_patternA

Complete pattern analysis in one call: search + follow-through + AI summary.

This is the recommended tool for most use cases. It combines search_charts,
get_follow_through, and get_pattern_summary into a single call.

Returns matching patterns, forward return statistics (1/3/5/10 day),
outcome distribution, and an AI-written summary.

Args:
    query: Symbol + date, e.g. 'AAPL 2024-06-15' or 'TSLA 6/15/24 3d'
    timeframe: Session: rth (regular hours), premarket, rth_3d, rth_5d, or auto
    top_n: Number of results (1-50)
    include_summary: Whether to include AI-generated summary (default True)
get_discover_picksA

Get top daily chart pattern picks ranked by interest score.

Returns the most interesting patterns from the automated nightly scan,
with AI summaries, predicted returns, and confidence scores.

Args:
    date: Date in YYYY-MM-DD format (defaults to latest available)
    limit: Max picks to return (1-50, default 20)
search_batchA

Search for similar patterns across multiple symbols at once.

Batch version of search_charts — runs parallel searches for up to 20 symbols
on the same date and returns forward return statistics for each.

Args:
    symbols: List of ticker symbols (max 20), e.g. ['AAPL', 'MSFT', 'NVDA']
    date: Date in YYYY-MM-DD format
    timeframe: Session: rth, premarket, rth_3d, rth_5d (default rth)
    top_n: Number of results per symbol (1-50)

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/grahammccain/chart-library-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server