
Visuals MCP
Displays data in interactive UI components through MCP. Exposes tools for rendering TanStack tables with sorting, filtering, and pagination, Recharts visualizations (line, bar, pie, scatter, composed), image previews with metadata, master-detail views for collections, tree structures with expand/collapse, and customizable lists with drag and drop. Selection and interaction state flows back to the LLM via updateModelContext, so the agent knows what you clicked or filtered. Useful when you need richer output than text for browsing datasets, file trees, dashboards, or task lists. Runs via stdio, ships as an npm package, and includes a VS Code extension that auto-registers with Copilot Chat.
- GitHub stars
- 4
- tool
- 1
- transport
- STDIO
- last updated
- Apr 7, 2026
Tools
1 toolsPublic tool metadata for what this MCP can expose to an agent.
display_chartUse `display_chart` to render one or more interactive charts in the MCP client.
Use `display_chart` to render one or more interactive charts in the MCP client.
No parameter schema in public metadata yet.
Sponsors
Readme
MCP Visuals Server
An MCP (Model Context Protocol) server that provides interactive visualizations for AI agents. Display data in rich, interactive formats including tables with TanStack Table, charts with Recharts, image previews with metadata, master-detail views for browsing collections, tree views for hierarchical data, and customizable lists with drag-and-drop reordering.
Quick Install
Features
Table Visualization
Details
- Repository
- github.com/harrybin/visuals-mcp
- Package
@harrybin/visuals-mcp- Transport
- STDIO
- Registry
- MCP registry, active