Chart Library MCP Server

Works with: Claude Desktop | Claude Code | ChatGPT | GitHub Copilot | Cursor | VS Code | Any MCP client

Ask your AI agent "what happened the last 10 times a chart looked like this?" and get a real answer.

24 million pattern embeddings. 10 years of history. 15,000+ stocks. One tool call.

> "What does NVDA's chart look like right now?"

Found 10 similar historical patterns for NVDA (2026-04-04, RTH timeframe):

  Closest match: AAPL 2023-05-12 (distance: 0.41)

  Forward returns across all 10 matches:
    1-day:  +0.8% avg  (7/10 positive)
    5-day:  +3.1% avg  (8/10 positive)
    10-day: +4.7% avg  (7/10 positive)

  Summary: NVDA's current consolidation near highs mirrors 10 historical
  setups, most notably AAPL's May 2023 pre-breakout pattern. 8 of 10
  resolved higher within a week, with a median 5-day gain of +2.8%.

No hallucinated predictions. No refusals. Just factual historical data your agent can cite.

Quick Start

pip install chartlibrary-mcp

Claude Desktop (One-Click Install)

Download the chart-library-1.1.1.mcpb extension file and open it with Claude Desktop for automatic installation.

Claude Code

claude mcp add chart-library -- chartlibrary-mcp

Claude Desktop (Manual)

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "chart-library": {
      "command": "chartlibrary-mcp",
      "env": {
        "CHART_LIBRARY_API_KEY": "cl_your_key"
      }
    }
  }
}

Cursor / VS Code

Add to .cursor/mcp.json or VS Code MCP settings:

{
  "servers": {
    "chart-library": {
      "command": "chartlibrary-mcp",
      "env": {
        "CHART_LIBRARY_API_KEY": "cl_your_key"
      }
    }
  }
}

GitHub Copilot (VS Code)

Add to .vscode/mcp.json in your project (this file is already included in the chart-library repos):

{
  "servers": {
    "chart-library": {
      "command": "chartlibrary-mcp",
      "env": {
        "CHART_LIBRARY_API_KEY": "cl_your_key"
      }
    }
  }
}

Copilot Chat will auto-detect the MCP server when you open the project. Use @mcp in Copilot Chat to invoke tools.

ChatGPT (Developer Mode)

ChatGPT connects to MCP servers via remote HTTP endpoints. To set up:

1. Enable Developer Mode: Go to ChatGPT Settings > Apps > Advanced settings > Developer mode (requires Pro, Plus, Business, Enterprise, or Education plan)

2. Create a connector: In Settings > Connectors, click Create and enter:

   • Name: Chart Library

   • Description: Historical chart pattern search engine -- 24M patterns, 10 years of data

   • URL: https://chartlibrary.io/mcp

   • Authentication: No Authentication (or OAuth if using an API key)

3. Use in conversations: Select "Developer mode" from the Plus menu, choose the Chart Library app, and ask questions like "What does NVDA's chart look like historically?"

Note: The remote endpoint at https://chartlibrary.io/mcp uses Streamable HTTP transport. If you need SSE fallback, use https://chartlibrary.io/mcp/sse.

Remote MCP Endpoint

For any MCP client that supports remote HTTP connections:

https://chartlibrary.io/mcp

This endpoint supports both Streamable HTTP and SSE transports, no local installation required.

Free tier: 200 calls/day, no credit card required. Get an API key at chartlibrary.io/developers or use basic search without one.

What Can Your Agent Do With This?

"Should I be worried about my TSLA position?"

> get_exit_signal("TSLA")

  Signal: HOLD (confidence: 72%)
  Similar patterns that exited early: 3/10 would have avoided a drawdown
  Similar patterns that held: 7/10 gained an additional +2.1% over 5 days
  Recommendation: Pattern suggests continuation. No exit signal triggered.

"What sectors are rotating in right now?"

> get_sector_rotation()

  Leaders (30-day relative strength):
    1. XLK  Technology     +4.2%
    2. XLY  Cons. Disc.    +3.1%
    3. XLC  Communication  +2.8%

  Laggards:
    9. XLU  Utilities      -1.4%
   10. XLP  Cons. Staples  -2.1%
   11. XLRE Real Estate    -3.3%

  Regime: Risk-On (growth > defensives)

"What happens to AMD if SPY drops 3%?"

> run_scenario("AMD", spy_change=-3.0)

  When SPY fell ~3%, AMD historically:
    Median move:  -5.2%
    Best case:    +1.1%
    Worst case:  -11.4%
    Positive:     18% of the time

  AMD shows 1.7x beta to SPY downside moves.

19 Tools

Core Search (7 tools)

Market Intelligence (7 tools)

Trading Intelligence (4 tools)

Utility (1 tool)

How It Works

Chart Library uses 24 million pre-computed pattern embeddings (multi-channel numerical encodings of price, volume, volatility, and VWAP) indexed with pgvector for sub-10ms similarity search.

When your agent calls analyze_pattern("NVDA"), the server:

1. Computes NVDA's current embedding from the latest market data

2. Finds the 10 nearest neighbors by L2 distance across all stocks and dates

3. Looks up what happened 1, 3, 5, and 10 days after each historical match

4. Generates a plain-English summary via Claude Haiku

The result: factual, citation-ready statements like "8 of 10 similar patterns gained over 5 days" that your agent can present without hallucinating or hedging.

API Key

Get your key at chartlibrary.io/developers.

export CHART_LIBRARY_API_KEY=cl_your_key

Links

• Website

• API Documentation

• Developer Portal

• Regime Tracker

• Python SDK | JavaScript SDK

Chart Library provides historical pattern data for informational purposes. Not financial advice.