Best for
- Frontend teams already using Storybook who want AI agents to help draft or test component stories
- Developers using Claude Code or Codex who want ready-made Storybook integration
An officially maintained (storybookjs) MCP addon that runs inside the Storybook dev server, exposing component data over streamable-http so AI agents can write and validate stories; still experimental and only useful for local Storybook-based projects.
Strongest · Maintenance 13/20 Weakest · Reliability 8/20
Static review · not runListed 2026-08-26
Read the FMRS scoring method →Runtime:Node.js 24+
npm install --save-dev @storybook/addon-mcp (or pnpm/yarn), then include @storybook/addon-mcp in the addons list of .storybook/main.ts.pnpm storybook); the MCP server runs alongside it, listening by default at http://localhost:6006/mcp.claude plugin marketplace add storybookjs/mcp@main) to have the MCP connection configured automatically.{"mcpServers":{"storybook":{"type":"streamable-http","url":"http://localhost:6006/mcp"}}}
Shown for Claude Code. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.
{
"servers": {
"storybook": {
"type": "streamable-http",
"url": "http://localhost:6006/mcp"
}
}
}
Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).
claude mcp add --transport http storybook http://localhost:6006/mcp
Run it in a terminal; replace any <…> placeholders with your own values first.
Start Storybook and connect your client to http://localhost:6006/mcp; list-all-documentation and preview-stories should appear in the tool list, or confirm with a curl POST to /mcp calling tools/list.
Once connected, you can ask your AI assistant things like:
No matching tools
Listed from the project's documentation, not tested by this site.
Storybook MCP Addon (npm package @storybook/addon-mcp) is maintained by storybookjs, the official Storybook GitHub organization. It runs an MCP server as part of your local Storybook dev server, exposing component information and development workflows over streamable-http at http://localhost:6006/mcp (port configurable via a --port argument). This lets AI agents read component documentation, author new stories, and verify how they render. The monorepo also ships companion Claude Code and Codex plugins that auto-configure this MCP server. The README notes the project is experimental and under active development, so APIs and architecture may change.
Upstash's official server providing up-to-date third-party library docs for AI coding assistants
AI-powered NPM package analysis MCP server
An independent control layer that gives AI coding agents budgets, brakes, and receipts
GitHub's official MCP server for managing repos, issues, PRs, and workflows via natural language
Source revision 4589b69a0812 Data synced 2026-10-12 Read the FMRS scoring method