Build an interactive Plotly figure from tabular data and return it as JSON.

Pass data as a list of records and choose a chart kind. The server constructs and validates the figure and returns it as a JSON string (the output of fig.to_json()). A frontend can parse the string and render it directly with plotly.js. Returning a string keeps the response a single text content block, which is robust across MCP clients and transports.

Construct and validate a Plotly figure from a full figure spec.

Use this when you want full control over traces and layout. The server builds the figure, which surfaces schema errors, and returns it as a JSON string.

Render a Plotly figure spec to a standalone HTML document string.

The returned HTML can be saved as a .html file or embedded directly. Use this when a consumer wants a portable, viewable artifact rather than the raw figure JSON.

Build a Plotly figure from data and a natural-language description.

An AI agent (Gemini, driven by opencode running on the server) writes and runs Python plotting code against the provided data to satisfy the description, then returns the resulting figure as JSON, the same shape quick_plot and create_figure return. Slower than the other tools because it runs a full code-generation loop, but it handles open-ended chart requests.