Ploti is a free, open-source MCP tool that renders 43 chart types as interactive widgets inside Claude, ChatGPT, Gemini, Cursor, and VS Code. No account required.
By Lola Reeves
Charts have always lived outside AI conversations. You run an analysis, get a table of numbers, and then open a separate tool to visualize it. Ploti changes that. It is a free, open-source MCP server that renders 43 chart types as interactive widgets directly inside Claude, ChatGPT, Gemini, Cursor, VS Code, and Goose.
No account. No API key. One URL to connect. MIT licensed.
When you connect Ploti to your AI assistant, you can ask it to make a chart the same way you ask it to write code or summarize a document. The chart appears inline in the conversation as an interactive widget: hover for tooltips, toggle legend items, switch between light and dark themes.
Ploti supports 43 chart types. The full list includes bar, grouped bar, stacked bar, horizontal bar, line, multi-line, area, stacked area, scatter, bubble, pie, donut, waterfall, candlestick, OHLC, heatmap, treemap, sunburst, sankey, radar, funnel, gauge, and more. The engine renders deterministic SVG output, meaning the same data produces the same chart every time.
Every chart carries a "Made with Ploti by Ooty" badge linking back to ooty.io/ploti. There is a copy-embed button that outputs an <iframe> snippet for embedding charts in blog posts, Substack issues, or any HTML page. There is also a PNG fallback for contexts that do not support interactive rendering.
The connection process is the same as connecting any MCP server. No credentials needed.
Connection address: https://ooty.io/ploti/mcp
Claude (web or desktop): Open Settings, click Connectors, click Add custom connector, paste the address above.
ChatGPT: Requires a Pro, Team, Enterprise, or Edu plan. Enable Developer Mode in Settings first (look for it in Connectors, Beta features, or Advanced). Then go to Settings, Connectors, Add Connector, and paste the address.
Gemini: Open Settings, find Extensions or Integrations, click Add custom integration, paste the address.
Cursor and VS Code: Add to your mcp.json with just the URL. No authorization header needed.
Head of Content at Ooty. Covers AI marketing research and data strategy.
Ooty connects your marketing platforms to your AI assistant. Ask ChatGPT, Claude, or Gemini a question and get an answer pulled from Google Analytics, Search Console, Google Ads, Meta, YouTube, Amazon, HubSpot, and more. No exports, no dashboards, no tab switc
Most marketing teams use AI the same way: copy data from one dashboard, paste it into ChatGPT, Gemini, or Claude, ask a question, and hope the answer is useful. The AI does its best with a screenshot or a CSV export, but it is working with a snapshot, not your
When you connect ChatGPT, Gemini, or Claude to your Google Analytics account through Ooty, your Google password never touches our systems. Neither does your Meta login, your Amazon credentials, or any other platform password. We use OAuth, the same authenticat
{
"mcpServers": {
"ploti": {
"url": "https://ooty.io/ploti/mcp"
}
}
}After connecting, ask your AI to make a chart. A working prompt: "Make a bar chart showing monthly revenue for Q1: January 42000, February 38000, March 51000."
Ploti is a distribution play, not a SaaS product. Every chart embeds a link back to ooty.io/ploti. When someone embeds a chart on their blog, their readers see the badge and follow the link. The backlink strategy is the point. The chart tool is the vehicle.
The code is open source under the MIT license in the Ooty monorepo on GitHub. The engine, widget, and MCP server are all there. Paying Ooty subscribers get a watermark-off flag that removes the badge from their charts.
Ploti is built by the Ooty team. Ooty is a paid marketing intelligence platform that connects tools like Google Search Console, Meta Ads, and Amazon PA-API directly to AI assistants. The full Ooty product suite covers SEO, analytics, ads, social, commerce, video, and CRM.
Ploti started as an internal charting layer for Ooty's own reports. The chart engine went through six build phases and 1,239 tests before shipping publicly. It handles dimension caps, data point limits, SVG byte caps, and plugin sandbox isolation. The widget uses Shadow DOM encapsulation to keep the badge in place.
Connect address: https://ooty.io/ploti/mcp
Source code: github.com/abcreativ/ooty
Documentation: ooty.io/docs
Ask your AI to make a chart.