mcp-server-chart
MCP Server Chart is a TypeScript-based visualization server that generates 26+ chart types using AntV libraries. It integrates with AI models via the Model Context Protocol, enabling chart generation and data analysis capabilities in LLM-driven applications.
Key facts
Objective fields from the source. Values we can't verify are shown as “Unknown” rather than guessed.
| Field | Value |
|---|---|
| Repository | antvis/mcp-server-chart |
| Owner | antvis |
| Primary language | TypeScript |
| License | MIT — OSI-approved |
| Stars | 4.2k |
| Forks | 400 |
| Open issues | 12 |
| Latest release | 0.9.10 (2026-02-25) |
| Last updated | 2026-05-06 |
| Source | https://github.com/antvis/mcp-server-chart |
What mcp-server-chart is
Built on Node.js/TypeScript, it exposes MCP tools for programmatic chart generation across multiple chart types (area, bar, pie, sankey, network graphs, maps, etc.). Supports multiple transport protocols (stdio, SSE, streamable) and can be deployed standalone, in Docker, or as an npm package.
Get the mcp-server-chart source
Clone the repository and explore it locally.
git clone https://github.com/antvis/mcp-server-chart.gitcd mcp-server-chart# follow the project's README for install & configurationNeed it deployed, integrated, or customized instead? DEV.co ships production installs.
Best use cases
Implementation considerations
- Transport protocol choice depends on deployment context: stdio for stdio-based MCP clients, SSE/streamable for HTTP-based integrations (Desktop app, web, Docker).
- Geographic features require internet connectivity to AMap service; consider network policies and regional restrictions (China-focused).
- MCP tools expose chart generation as discrete functions; requires MCP-compatible client integration (Claude, VSCode, Cline, Dify, or custom MCP hosts).
- Environment variables support tool filtering (DISABLED_TOOLS), custom service endpoints (VIS_REQUEST_SERVER), and service metadata (SERVICE_ID) for flexibility.
- Docker deployment provided; npm global install or npx execution are simpler alternatives for local/desktop use.
When to avoid it — and what to weigh
- Real-time streaming analytics at scale — No evidence of optimization for high-frequency updates or large-scale streaming data; designed for on-demand chart generation rather than continuous monitoring dashboards.
- Global geographic mapping required — Geographic charts (district-map, pin-map, path-map) use AMap service and are documented as China-only; unsuitable if worldwide mapping is required.
- Offline-only or air-gapped environments — Geographic features depend on external AMap service; SSE and streamable transports require network access; limited support for fully offline operation.
- Custom chart types or deep visualization control — Constrained to 26 predefined chart types; limited flexibility for highly specialized or proprietary visualization requirements not covered by AntV.
License & commercial use
MIT License: permissive open-source license allowing unrestricted use, modification, and distribution in proprietary and commercial projects, provided original copyright and license notice are retained.
MIT License explicitly permits commercial use without modification restrictions. Safe for commercial deployments, closed-source products, and SaaS platforms. No licensing fees or attribution demands beyond standard copyright notice.
DEV.co evaluation signals
Editorial assessment — not user reviews. Directional, with an explicit confidence level.
| Signal | Assessment |
|---|---|
| Maintenance | Active |
| Documentation | Adequate |
| License clarity | Clear |
| Deployment complexity | Low |
| DEV.co fit | Strong |
| Assessment confidence | High |
No explicit security policies or vulnerability disclosure process documented. Consider: MCP server runs local or in controlled network; input validation for chart data (untrusted JSON) should be reviewed; external AMap service calls expose geographic queries; no mention of rate limiting, authentication, or input size constraints.
Alternatives to consider
Plotly / Dash
Full-featured Python-based visualization framework with rich interactivity; better for standalone apps, but heavier and less LLM-native integration.
ECharts (Apache) + custom MCP wrapper
Similar chart library with broader international support and no geographic service dependency; requires custom MCP server development.
Observable Plot / Vega-Lite
Declarative, lightweight visualization grammars; more portable and standards-based, but less AI-assistant integration out-of-the-box.
Build on mcp-server-chart with DEV.co software developers
Integrate mcp-server-chart to enable intelligent, on-demand visualization in Claude, VSCode, and custom LLM applications. Deploy via npm, Docker, or cloud platforms in minutes.
Talk to DEV.coRelated open-source tools
Surfaced by semantic similarity across the DEV.co open-source index.
Related on DEV.co
Explore the category and the services that help you build with it.
mcp-server-chart FAQ
Can I use this in production for a SaaS platform?
What is the difference between MCP transport protocols (stdio, SSE, streamable)?
Does it support non-Chinese geographic maps?
How do I customize the chart output format?
Custom software development services
Need help beyond evaluating mcp-server-chart? DEV.co is a software development agency offering software development services and web development for teams of every size. Our software developers and web developers build custom software, web applications, APIs, and mcp servers integrations — and maintain them long-term.
Add Chart Generation to Your AI Application
Integrate mcp-server-chart to enable intelligent, on-demand visualization in Claude, VSCode, and custom LLM applications. Deploy via npm, Docker, or cloud platforms in minutes.