The Chart Library MCP Server provides access to a historical chart pattern search engine, allowing users to analyze stock patterns and their outcomes based on 24 million pre-computed embeddings.
From the registry: Historical chart-pattern intelligence for AI agents. 25M+ embeddings, 19K+ symbols, 10y history.
$ pip install chartlibrary-mcphttps://pypi.org/project/chartlibrary-mcp/Please install the `chart-library` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install via pip** — Install the chartlibrary-mcp Python package Run: `pip install chartlibrary-mcp` (https://pypi.org/project/chartlibrary-mcp/)
Optional prerequisites:
- API Key (optional) — Get a free API key (200 calls/day) at chartlibrary.io/developers (https://chartlibrary.io/developers)
Canonical MCP server config (stdio transport):
- command: `chartlibrary-mcp`
- args: []
- optional environment variables:
- `CHART_LIBRARY_API_KEY`: Chart Library API key (free tier: 200 calls/day) (example: `cl_<your-api-key>`)
Note: Also available as remote endpoint https://chartlibrary.io/mcp (Streamable HTTP/SSE). 24M pattern embeddings, historical chart pattern search.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.CHART_LIBRARY_API_KEYrequiredAPI key for accessing the Chart Library servicesTrending hip-hop artist momentum scores across four cultural dimensions.
Official PostHog MCP Server for product analytics, feature flags, experiments, and more.
Official OpenMetadata MCP: governed context and business semantics for AI assistants and agents.