Log inSubmit server
Chartone logo

Chartone

Render themed charts with inline images and hosted URLs for email, Slack, PDFs, and dashboards.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Chartone

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "chartone-2": {
      "command": "npx",
      "args": [
        "-y",
        "@chartone/mcp"
      ],
      "env": {
        "CHARTONE_API_KEY": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

We couldn’t confirm it starts correctly

The install command started, but didn't respond the way we expected when we tried to talk to it.

npx -y @chartone/mcp

initialize succeeded but no response to tools/list.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 3d ago.

Overview

The chartone MCP server renders themed charts and returns both an inline image and a persistent hosted URL. It exposes render_chart for explicit chart type, data, and theme inputs, plus suggest_chart for choosing a chart type and theme from data and an intent. Use it when an AI agent needs chart output that can be embedded in emails, Slack messages, PDFs, or dashboards. It can run locally through stdio or through a hosted MCP endpoint.

Use cases

  • Render themed charts for email messages
  • Embed chart URLs in Slack updates
  • Generate charts for PDFs and dashboards
  • Suggest a chart type from data and intent

Key features

  • Render charts from explicit inputs
  • Suggest chart types and themes
  • Return inline images
  • Provide hosted chart URLs
  • Support local stdio and hosted MCP access
  • Offer anonymous watermarked rendering

Tools2

What Chartone lets your agent do. Expand a tool for its parameters.

Self-reported~6 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

5/5 checks healthy over the last 39d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 7d ago via OSV.dev · @chartone/mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads384Package downloads in the last 30 days.
Last commit5mo agoMost recent push to the default branch.
Install checkInconclusiveStarted but did not complete the MCP handshake in our test.
Tools exposed2Callable tools this server registers over MCP.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How Chartone works

What chartone MCP server does

The chartone MCP server lets an AI agent create themed charts through MCP. It returns two forms of output for each render: an inline image for immediate display and a hosted URL that can be reused in content such as emails, Slack messages, PDFs, and dashboards.

The service supports two workflows. Use render_chart when the agent or application already knows the chart type, data, and theme. Use suggest_chart when the input is data plus a descriptive goal, such as showing quarterly trends, and the service should select the chart type and theme before rendering it.

How it works

A local MCP client starts the package with npx -y @chartone/mcp. The client then communicates with the server over the standard local configuration used by supported MCP applications. The same service also exposes a beta hosted endpoint at https://api.chartone.dev/mcp for cloud agents that cannot run a local stdio process.

Requests to the hosted endpoint use HTTP POST with an optional Bearer token and MCP request bodies such as tools/list or tools/call. Both available tools produce the inline image and hosted URL as their result.

The chartone MCP server can run without an API key. Anonymous requests return watermarked charts. An API key enables the account-based service, while paid tiers remove the watermark and extend the lifetime of hosted URLs.

Setup and configuration

For Claude Desktop, add an MCP server entry to the platform’s configuration file and set the command to npx, with -y and @chartone/mcp as arguments. The optional CHARTONE_API_KEY environment variable can contain a key obtained from chartone.dev. Restart Claude Desktop after changing its configuration.

Cursor, Zed, and Windsurf use the same general configuration shape, although their settings-file locations differ. The project points to the ChartOne MCP documentation for current paths. Cloud agents can instead send MCP requests to the hosted beta endpoint and optionally include Authorization: Bearer sk-....

Tools and capabilities

  • render_chart accepts an explicit chart type, data, and theme, then renders the result.
  • suggest_chart accepts data and an intent, selects a chart type and theme, and renders the result.
  • Both tools return an inline image and a persistent hosted URL.
  • Outputs can be used in emails, Slack messages, PDFs, and dashboards.
  • Anonymous use is available with a watermark.

Limitations and notes

URL lifetime depends on the account tier: paid tiers extend it, while the documentation does not specify an exact duration. Anonymous charts include a watermark. The material also does not define supported chart types, data schemas, theme names, rate limits, or API-key quotas beyond noting that the free tier includes a render quota.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Chartone

chartone is an MCP server that connects AI agents to ChartOne’s chart-rendering service through local stdio or hosted HTTP MCP. Its main tools are render_chart, which uses an explicit type, data, and theme, and suggest_chart, which selects a chart type and theme from data and intent. Both return an inline image and URL.

Install it by configuring your MCP client to run npx with -y and @chartone/mcp as arguments. Claude Desktop uses its MCP configuration file, while Cursor, Zed, and Windsurf use the same configuration shape in their MCP settings. Add CHARTONE_API_KEY if you want to use an account key.

Yes, anonymous use is supported, but the resulting charts are watermarked. Add an optional Bearer token for the hosted endpoint or set CHARTONE_API_KEY in a local client configuration. The API key is available by signing up at chartone.dev.

It provides render_chart and suggest_chart. render_chart renders a chart from an explicit type, data, and theme. suggest_chart receives data and an intent, chooses the chart type and theme, and renders it. Both tools return an inline image and a hosted URL.

Related MCP servers

All in Data Visualization All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewChartone AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/chartone-2?style=directory)](https://allmcps.com/mcp/chartone-2)
HTML Embed
<a href="https://allmcps.com/mcp/chartone-2"><img src="https://allmcps.com/api/badge/chartone-2?style=directory" alt="Chartone on AllMCPs" /></a>