How to Use an MCP Server for Stock Analysis with Claude

What Is MCP?

Model Context Protocol (MCP) is an open standard that lets AI assistants like Claude connect to external data sources and tools. Instead of copying data into a prompt, you install an MCP server that gives the AI direct access to a service's API. The AI decides when to call which tool based on your question — no manual API calls, no code, no prompt engineering.

Chart Library's MCP server gives Claude (and any MCP-compatible AI) access to 25M+ pre-computed chart pattern embeddings, real-time regime data, sector analysis, and forward return statistics. Ask a question in plain English, and the AI calls the right tools behind the scenes.

Installation: Two Commands

The MCP server is published on PyPI and takes about 30 seconds to set up. You need Python 3.9+ and a free Chart Library API key.

• Install the package: pip install chartlibrary-mcp
• Get a free API key at chartlibrary.io/developers (200 calls/day on the free tier)
• Add the server to Claude Desktop: open Settings > Developer > MCP Servers, click 'Add,' and enter the command: chartlibrary-mcp --api-key YOUR_KEY
• Restart Claude Desktop. You'll see the Chart Library tools appear in the tools panel.

What the 19 Tools Do

The MCP server exposes a curated tool surface organized into a few intent groups. You never need to call them directly — Claude picks the right tool based on your question. But knowing what's available helps you ask better questions.

• Pattern Intelligence (3 tools): Search for similar chart patterns by ticker, analyze a specific ticker+date combination, and get full intelligence reports with AI summaries and forward return statistics.
• Market Context (4 tools): Get the current market regime for SPY/QQQ, check sector rotation rankings, detect crowding (many stocks trading the same pattern), and run scenario analysis for hypothetical market moves.
• Discovery (3 tools): Browse today's top patterns from the discover page, get trending tickers, and find the most interesting setups ranked by volume and pattern quality.
• Portfolio & Alerts (4 tools): Add holdings, get portfolio pattern analysis, set up pattern alerts, and check alert history.
• Data & Utilities (5 tools): Look up ticker details, get historical price data, check API usage, retrieve forward test accuracy stats, and access the track record dashboard.

Example Conversation with Claude Desktop

Here's a real conversation showing how Claude uses the MCP tools automatically. You just ask questions — Claude decides which tools to call.

You: "What does NVDA's chart look like right now? Anything interesting?" Claude calls: get_intelligence(symbol="NVDA") Claude: "NVDA's current intraday pattern closely matches 10 historical setups. The top match is AMD from August 2024 at 93% similarity. Looking at forward returns across all matches: the average 5-day return is +1.6% with 7 of 10 matches moving higher. The AI summary describes this as a post-earnings consolidation pattern with historical precedent favoring upside continuation, though 2 of the 10 matches saw drawdowns of 3%+ before recovering."

You: "What's the broader market doing? Should I be worried about anything?" Claude calls: get_regime(), get_crowding() Claude: "The current SPY regime most closely resembles March 2024 — a slow grind higher on moderate volume. 8 of 10 similar periods saw gains over the next 10 days. However, the crowding detector shows elevated correlation across tech stocks right now, which historically precedes short-term pullbacks in about 40% of cases. Not a red flag, but worth monitoring."

MCP vs. REST API: When to Use Which

The MCP server and the REST API access exactly the same data and endpoints. The difference is how you interact with them.

Use MCP when you want conversational access — asking questions in natural language, getting synthesized answers, and having the AI chain multiple calls together automatically. It's ideal for research sessions, market check-ins, and exploratory analysis where you don't know exactly what you're looking for.

Use the REST API when you're building automated systems — trading bots, dashboards, scheduled reports, or any programmatic workflow where you need structured JSON responses and precise control over which endpoints you call. The API is also better for high-volume use cases since you can batch requests and handle rate limits programmatically.

• Conversational research and exploration: MCP
• Automated trading systems and bots: REST API
• Building dashboards or apps: REST API
• Ad-hoc market analysis during the trading day: MCP
• Multi-agent workflows (LangChain, CrewAI): Either — MCP for simple setups, REST API for custom tool definitions

Get Started

The MCP server is free to install and the free API tier gives you 200 calls per day — more than enough for a full day of research conversations. Install it with pip install chartlibrary-mcp, add your API key, and start asking Claude about any stock, market regime, or chart pattern.

For more advanced use cases, check out the LangChain and CrewAI tutorials on the Chart Library blog, or browse the full API documentation at chartlibrary.io/developers.