Interactive charts that live inside your customers' agent. Composable, plugin-based, and made to scale, built by AI-native developers obsessed with data.
npm install @bonnard/mcp-chartsWhy use Bonnard Charts?
A sophisticated inference engine that produces high quality charts from queries
Works with text-to-SQL or semantic layers.
Devs avoid building any frontend code, we handle that
One widget that works across all MCP apps. You don't maintain per-host rendering code.
Interactive widgets, not static SVGs
Beautiful-by-default and native to the client. Brand, theme and formatting adjustable.
Visuals render cleanly in every agent client
Claude
ChatGPT
Cursor
Gemini
CopilotEasy MCP visuals for data.
One function adds a charting tool to your MCP server. Pass a query callback and skip the frontend.
- import { addCharts } from "@bonnard/mcp-charts";
- addCharts(mcpServer, { // add a `visualize` tool and MCP app to your mcp
- runSql: (sql) => db.query(sql), // pass a query callback
- });
Built for the agent, not just the user.
An agent can only use a tool it can read. The visualize tool is shaped for how the model calls it, not just for the human looking at the chart.
Managed token context, not raw dumps
Compact text summaries and row sampling keep tool output small and readable.
Errors that guide the next action
Clear errors and feedback loops steer the agent toward the correct call.
Less hallucination surface
We push deterministic work out of the model and into the code.
Clear tool descriptions
The agent knows exactly how and when to call the tool.
Take control of your data presentation.
It's the most important part of your experience. Don't hand it to the agent to improvise in artifacts or generated HTML.
Bonnard ChartsHandled for you
Charts built for agents.
Render charts in any agent client, generated from real query data.
ClaudeChatGPTCursorGeminiCopilot