MCP Servers

Chart Library

Historical stock pattern intelligence for AI agents. Search 24M pre-computed chart pattern embeddings across 15K stocks and 10 years. 19 tools: pattern similarity search, forward returns, regime analysis, anomaly detection, sector rotation, earnings reactions, correlation shifts, scenario analysis, and more. Returns what happened historically when charts looked like this — compliance-safe

README

Chart Library MCP Server

A compliance-safe way for AI agents to discuss stocks using real historical data.

Instead of hallucinating predictions or refusing to answer, your agent can say: "The last 10 times a chart looked like NVDA, 7 went up over 5 days (avg +3.1%)." This is factual historical data from 24 million pattern embeddings across 10 years and 15,000+ stocks — not financial advice, not predictions, just what happened before.

Install

pip install chartlibrary-mcp

Usage with Claude

# Claude Code
claude mcp add chart-library -- chartlibrary-mcp

# Or run directly
CHART_LIBRARY_API_KEY=cl_your_key chartlibrary-mcp

Tools (19)

Core Search

Tool	Description
`analyze_pattern`	Search + forward returns + AI summary in one call (recommended)
`search_charts`	Find 10 most similar historical patterns
`get_follow_through`	Forward returns (1/3/5/10-day) for matches
`get_pattern_summary`	AI-generated plain-English summary
`get_discover_picks`	Daily top patterns ranked by interest score
`search_batch`	Multi-symbol parallel search (up to 20)
`get_status`	Database stats and coverage

Market Intelligence

Tool	Description
`detect_anomaly`	Check if a stock's pattern is unusual vs history
`get_volume_profile`	Intraday volume breakdown vs historical average
`get_sector_rotation`	Which sectors are leading/lagging
`get_crowding`	Are too many stocks signaling the same direction?
`get_earnings_reaction`	Historical earnings gap reactions
`get_correlation_shift`	Stocks breaking from usual market correlation
`run_scenario`	What happens to a stock when the market moves X%?

Trading Intelligence

Tool	Description
`get_regime_win_rates`	Pattern win rates filtered by current market regime
`get_pattern_degradation`	Are signals degrading vs historical accuracy?
`get_exit_signal`	Pattern-based exit recommendations for open positions
`get_risk_adjusted_picks`	Picks scored by Sharpe-like risk/reward ratio

Utility

Tool	Description
`report_feedback`	Report errors or suggestions

Example Conversation

User: What does NVDA's chart look like right now?

Claude (using Chart Library): NVDA's current pattern matches 10 historical setups. The closest is AAPL from May 2016 (93% similarity). Of the 10 matches, 8 went up over 5 days with an average gain of +3.0%. The current market regime resembles the post-SVB period of early 2023, which historically resolved bullishly.

API Key

Get a free API key (500 calls/day) at chartlibrary.io/developers.

Set it as an environment variable:

export CHART_LIBRARY_API_KEY=cl_your_key

Recommended Servers

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official

Featured

TypeScript

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official

Featured

Local

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official

Featured

TypeScript

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official

Featured

Python

E2B

Using MCP to run code via e2b.

Official

Featured

Neon Database

MCP server for interacting with Neon Management API and databases

Official

Featured

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official

Featured