Access 24M chart pattern embeddings and regime-conditioned intelligence through 23 MCP tools for context-aware financial charting. Built for developers integrating advanced chart analysis and pattern recognition into AI workflows.
io.github.grahammccain/chart-library
Local install
STDIO
No auth required
How models use it and what it is built for.
Access 24M chart pattern embeddings and regime-conditioned intelligence through 23 MCP tools for context-aware financial charting. Built for developers integrating advanced chart analysis and pattern recognition into AI workflows.
Local install — runs as a subprocess.
Configuration this server reads at startup.
Chart Library API key (get free at chartlibrary.io/developers)
Where to find authoritative docs and source for Chart Library — Pattern Intelligence.
Paste any of these into Agent Studio after connecting Chart Library — Pattern Intelligence.
Common questions about connecting and running Chart Library — Pattern Intelligence.
What is the Chart Library MCP server?
It's an MCP server that exposes 23 tools for querying 24M chart pattern embeddings and regime-conditioned analysis. It helps developers integrate pattern recognition and historical chart intelligence into AI applications via the Model Context Protocol.
How do I authenticate with the Chart Library API?
Set the CHART_LIBRARY_API_KEY environment variable with your API key. You can get a free key at chartlibrary.io/developers. The server uses this key to authenticate all requests to the Chart Library backend.
How do I install and run this server?
Install via uvx: `uvx chartlibrary-mcp@1.2.0`. The server runs over stdio transport, so configure your MCP client to spawn it as a subprocess and pipe stdin/stdout to communicate with the 23 available tools.
What does 'regime-conditioned' mean in this context?
Regime-conditioned means the chart patterns and embeddings are tagged with market conditions (e.g., trending, ranging, high volatility) so you can filter patterns by the regime they historically occurred in, improving pattern relevance for your current market state.
Can I use this for real-time trading signals?
The server provides historical pattern matching and embeddings, not real-time signals. It's designed for analysis, backtesting, and pattern research within AI workflows; always validate any trading logic independently and consult financial advisors.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams