flint-chart
🪄 Flint is a visualization language that lets AI agents reliably create expressive, good-looking charts from simple, human-editable chart specs.
Flint Chart MCP is an MCP server that enables AI agents to generate expressive, well-designed data visualizations from compact, semantic chart specifications. Built by Microsoft Research, it uses a visualization language that leverages 70+ semantic data types to automatically handle layout, styling, and backend rendering without requiring agents to specify verbose parameters. Agents can create charts that compile to native Vega-Lite, ECharts, Chart.js, Plotly, or Excel formats, with support for formal visual themes like Economist, Swiss, and New York Times styles. The server can be accessed via a hosted endpoint or installed locally for large datasets.
Key Features
Use Cases
- 01Financial analysis where agents fetch stock data and create themed comparison charts
- 02Data journalism workflows requiring consistent visual identity across chart libraries
- 03Business reporting with agents generating branded visualizations in Excel or web formats
- 04Exploratory data analysis where agents quickly prototype multiple chart types from the same dataset
- 05Cross-platform chart generation needing the same specification to render in different visualization libraries
- 06Educational contexts where agents help users visualize statistical concepts with semantically-aware charts
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
flint-chart — FAQ
What is Flint Chart MCP?+
Flint Chart MCP is an MCP server that gives AI agents the ability to create polished data visualizations from simple, semantic chart specifications. It compiles these specs into native formats for Vega-Lite, ECharts, Chart.js, Plotly, or Excel.
How do I install Flint Chart MCP server?+
For quick access, use the hosted server at https://flint.data-formulator.ai/mcp in GitHub Copilot or Claude. For local installation with large datasets, run 'npx -y flint-chart-mcp' and configure your MCP client according to the MCP Server Guide.
Which AI clients work with Flint Chart MCP?+
Flint Chart MCP works with GitHub Copilot in VS Code (via MCP: Add Server → HTTP) and Claude (via Customize → Connectors → Add custom connector). Any MCP-capable client that supports remote HTTP or local MCP servers can use it.
Does Flint Chart MCP require API keys or credentials?+
No API keys are required to use the MCP server itself. However, if your agent workflow involves fetching data from external APIs (like Yahoo Finance), those services may require their own authentication.
Is Flint Chart MCP free to use?+
Yes, Flint Chart MCP is open source and released under the MIT license. Both the hosted server and the npm packages (flint-chart and flint-chart-mcp) are freely available.
What makes Flint different from having agents generate chart code directly?+
Flint uses semantic types and automatic layout decisions so agents don't need to manually specify verbose parameters for scales, axes, spacing, and styling. A single compact spec can compile to multiple backend formats, and formal themes ensure visual consistency across entire chart libraries.
How do I install flint-chart?+
Open the source repository on GitHub and follow its README. flint-chart is a mcp server — MCP Agents Market links you directly to the official repo.
Is flint-chart free?+
flint-chart is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.