AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
Dev Tooling/
flint-chart
flint-chart logo

flint-chart

Active·★ 4.4k·MIT·Updated 2026-10-21

Flint is a visualisation intermediate language from Microsoft that lets AI agents create polished charts from simple, human-editable chart specs. Instead of asking agents or developers to tune verbose settings such as scales, axes, spacing, labels and layout, the Flint compiler derives optimised settings from the data, semantic types, chart type and encodings. The result is a compact specification that agents can produce reliably, people can edit directly, and multiple backends can render as native Vega-Lite, ECharts or Chart.js specs.

The repository has two main components: flint-chart, a JavaScript and TypeScript library that compiles the same input into those three backends, and flint-chart-mcp, an MCP server that lets agents create, validate and render charts from a chat or coding environment. Features include semantic chart specs using 70+ semantic types (such as Rank, Temperature, Price or Country), automatic layout based on data cardinality and canvas constraints, 30+ chart types across the three backends, and an MCP server that offers templates, validation and an interactive chart view. Install with `npm install flint-chart` or `npx -y flint-chart-mcp`; a Python package is not yet released and the current port is a source-only preview. It is MIT licensed.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-10-18.

License
MIT
Latest release
0.5.1 · 2026-08-14
Last commit
2026-10-18
Contributors
20
Forks
247
Open issues and PRs
37
First published
2026-05-13
npm package
flint-chart 0.5.1 · 32,164 downloads last week

Source: GitHub, npm and PyPI public APIs.

#Visualization#Charting#AI Agents#Data Visualization#Compiler#Vega-Lite#ECharts#Chart.js
$ Install
$ npm install flint-chart
↗ Visit site★ GitHub
01

Features

01Semantic chart specifications using 70+ types (e.g., Rank, Temperature, Price, Country).
02Automatic layout and adaptation of sizing, spacing, labels, marks, and legends to data and constraints.
03Compilation to multiple backends, supporting 30+ chart types across Vega-Lite, ECharts, and Chart.js.
04Agent-ready chart authoring with an MCP server for interactive views and direct integration into chat/coding environments.
02

Why choose it

+Compact chart specs that an agent can write reliably and a person can edit, with layout and axes derived automatically.
+One input compiles to Vega-Lite, ECharts or Chart.js, covering 30+ chart types.
+70+ semantic types let the compiler choose sensible encodings from what each field means.
+MCP server to create, validate and render charts; MIT licensed and from Microsoft.
03

Trade-offs

!The Python package is not yet released; the current Python port is a source-only preview.
!It is a new intermediate language, so you learn Flint's spec format and semantic types instead of a backend's native format.
!It only generates charts through the three supported backends, and more backends are described as coming later.
04

Maintenance check

ActiveChecked: 2026-10-17
Last commit
2026-09-23
Commits, last 90 days
100+
Releases, last 90 days
4
Latest release
0.5.1 (2026-08-14)
Open issues
35
Recent issues with at least one comment
4/12
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 74, 124, 23, 5, 8, 23, 33, 12, 2, 0, 0, 0

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #102 Use `camelCase` instead of `kebab_case` in spec for consistency4 comments · 2026-08-17
  • #45 NTCharts2 comments · 2026-07-08
  • #80 Golden fixtures in shared/test-data no longer match the JS reference (705/705)1 comments · 2026-07-30
  • #67 No control over axis label font size (layout-computed ~10px, no scale knob)1 comments · 2026-07-21
  • #54 Add Plotly.js as a rendering backend1 comments · 2026-07-15

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Compatibility

JavaScript/TypeScript
Language
Verified via docs
Node.js
Runtime
Verified via docs
Python
Language
Verified via docs
MCP (Model Context Protocol)
Integration
Verified via docs
06

Quick start

1
$ npm install flint-chart
07

Use cases

↳AI agents generating sophisticated data visualizations from simple, high-level instructions.
↳Developers creating expressive charts without manually configuring verbose details like scales, axes, and layouts.
↳Integrating interactive chart creation, validation, and rendering directly within chat or coding environments using the MCP server.
↳Seamlessly switching between different JavaScript charting libraries (Vega-Lite, ECharts, Chart.js) using a unified input.
08

Alternatives

⚡Top VS:
VSterravision★1.7k→VSfigwright★1.1k→VSDebugMCP★572→VSpolymarket-paper-trader★504→
terravision logo
terravision★ 1.7k
Professional cloud architecture diagrams with official AWS, Azure and GCP icons, from Terraform code or a plain JSON graph. MCP server + agent skill.
VSCompare→
figwright logo
figwright★ 1.1k
Free, two-way Figma MCP server. Turn designs into framework-aware code, and push code back to the canvas. Works with Claude Code, Cursor, Codex, and any MCP client.
VSCompare→
DebugMCP logo
DebugMCP★ 572
Gift your VS Code agent a real debugger: breakpoints, stepping, inspection.
VSCompare→
polymarket-paper-trader logo
polymarket-paper-trader★ 504
Paper trading simulator for Polymarket
VSCompare→
Containarium logo
Containarium★ 310
The open-source, self-hostable, agent-native sandbox. Bring your own agent (Cursor, Claude Code, OpenCode); we run the box.
VSCompare→
fennara-godot-mcp logo
fennara-godot-mcp★ 310
Godot MCP workflow for AI agents using Fennara: diagnostics, scene validation, runtime feedback, screenshots, SemanticSearch, and patch-and-rerun loops.
VSCompare→
rutis logo
rutis★ 149
A plugin runtime for software that iterates on itself — the substrate where agents write, swap and hot-reload their own plugins in Rust, TypeScript, Python and Go, across processes and machines.
VSCompare→
jacobian logo
jacobian★ 319
Jacobian: an MCP server, CLI, and Python library that gives AI agents a composable toolbox of mathematical capabilities with inspectable artifacts and independent verification.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Compatibility06Quick start07Use cases08Alternatives
microsoft /
flint-chart
↗

Microsoft's compact chart language that compiles to Vega-Lite, ECharts and Chart.js

4.4k247MIT
Last commit2d ago
StatusActive
CategoryDev Tooling
Contributors20
Latest release0.5.1
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.