Chartly for AI agents
Chartly turns Chart.js configurations into rendered PNG or SVG images with permanent URLs, so a chart can be embedded or shared without a live app. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Chartly.
Render a chart as an image
Render a Chart.js configuration into a PNG image ready to drop into a report.
Create a permanent chart link
Create a permanent URL for a chart so it stays available even after the source data changes.
Look up an existing chart
Look up a previously created permanent chart before deciding whether to regenerate it.
3 Chartly actions, graded by risk.
Every Chartly action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
1Look things up. Allowed by default.
- chartly.get_permanent_chartGet Permanent Chart
write
2Create and change things. Allow, or ask the user first.
- chartly.create_permanent_chartCreate Permanent Chart
- chartly.render_chartRender Chart
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Chartly in three steps.
- 01Your users connect ChartlyThey add their Chartly api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “create Permanent Chart” can wait for the user to approve.
- 03Any agent can actYour agent calls Chartly through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('chartly', { read: 'allow', write: 'ask', // create_permanent_chart destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Chartly connects.
Users add their Chartly api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Chartly connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Chartly from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Chartly and Arc0, answered.
Can I use Chartly with Claude, ChatGPT or Cursor?
Yes. Connect Chartly to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Chartly actions you allow.
How do users connect Chartly?
Users add their Chartly api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Chartly actions can my agent take?
3 in total: 1 read, 2 write and 0 destructive, such as “create Permanent Chart”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Chartly?
Yes. Allow read actions and deny writes in the Chartly policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Chartly too?
Yes. The same Chartly connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Chartly into your agent.
Your users connect Chartly once, under your brand. Your agent gets 3 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan