Storybook MCP addon that lets Claude and other MCP clients inspect component documentation, generate stories, preview UI states, and run Storybook tests against a local Storybook project.
Storybook's MCP server and AI manifests are preview capabilities, and Storybook states that the API may change in future releases., The MCP server can guide an agent to generate components, write stories, preview states, and run tests. Review generated UI, stories, tests, and source changes before committing or shipping them., Storybook docs and stories are project-controlled input. Treat component docs, story text, examples, and addon output as untrusted context that can contain stale guidance or prompt-injection-like instructions., `run-story-tests` can execute interaction tests and browser-based component code. Do not run untrusted stories or tests with secrets, production credentials, or privileged browser sessions available., The default MCP endpoint is local to the Storybook dev server. Do not expose the local Storybook MCP endpoint or equivalent Storybook preview URLs to networks or tunnels unless access control and data exposure have been reviewed., When multiple Storybooks or MCP servers are configured, use descriptive server names so the model does not confuse design systems, toolsets, or component libraries.
Privacy notes
Storybook MCP tool results can expose component names, props, examples, docs, stories, design-system conventions, theme tokens, UI states, test results, accessibility findings, and story preview links., Storybook stories and previews can contain mock customer data, screenshots, private workflows, unreleased product UI, internal brand details, or business logic visible through component examples., Test output, accessibility reports, browser console logs, agent transcripts, screenshots, and generated summaries can retain Storybook content outside the normal repository and design-system access controls., Composed Storybooks can aggregate documentation and stories from multiple component libraries, so verify which composed sources are exposed before connecting an agent., Keep secrets, real user records, internal API tokens, and production credentials out of stories, play functions, test fixtures, and local Storybook environments used by AI agents.
Author
Storybook
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-03
Decision playbook
Review trust signals before you adopt
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
Compare context
Selected
0
Current score
78
Baseline
—
Delta
No baseline selected
No major trust-signal divergence detected in the current selection.
Source and provenance checks
Complete
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Done
Source provenance statusRequired
Marked as source-backed.
Done
Metadata reviewed
Registry metadata indicates a reviewed listing.
Done
Safety and privacy checks
Complete
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Done
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Done
Trust level risk gateRequired
Trust level does not block evaluation.
Done
Package and install checks
Needs review
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Done
Package verification flag
No package verification flag provided.
Pending
Checksum metadata
No checksum provided for downloaded artifact.
Pending
Compare-driven decision checks
Needs review
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
6 safety and 5 privacy notes across 5 risk areas. Review closely: credentials & tokens, permissions & scopes.
5 areas
SafetyGeneralStorybook's MCP server and AI manifests are preview capabilities, and Storybook states that the API may change in future releases.
SafetyExecution & processesThe MCP server can guide an agent to generate components, write stories, preview states, and run tests. Review generated UI, stories, tests, and source changes before committing or shipping them.
SafetyGeneralStorybook docs and stories are project-controlled input. Treat component docs, story text, examples, and addon output as untrusted context that can contain stale guidance or prompt-injection-like instructions.
SafetyCredentials & tokens`run-story-tests` can execute interaction tests and browser-based component code. Do not run untrusted stories or tests with secrets, production credentials, or privileged browser sessions available.
SafetyPermissions & scopesThe default MCP endpoint is local to the Storybook dev server. Do not expose the local Storybook MCP endpoint or equivalent Storybook preview URLs to networks or tunnels unless access control and data exposure have been reviewed.
SafetyExecution & processesWhen multiple Storybooks or MCP servers are configured, use descriptive server names so the model does not confuse design systems, toolsets, or component libraries.
PrivacyCredentials & tokensStorybook MCP tool results can expose component names, props, examples, docs, stories, design-system conventions, theme tokens, UI states, test results, accessibility findings, and story preview links.
PrivacyData retentionStorybook stories and previews can contain mock customer data, screenshots, private workflows, unreleased product UI, internal brand details, or business logic visible through component examples.
PrivacyPermissions & scopesTest output, accessibility reports, browser console logs, agent transcripts, screenshots, and generated summaries can retain Storybook content outside the normal repository and design-system access controls.
PrivacyGeneralComposed Storybooks can aggregate documentation and stories from multiple component libraries, so verify which composed sources are exposed before connecting an agent.
PrivacyCredentials & tokensKeep secrets, real user records, internal API tokens, and production credentials out of stories, play functions, test fixtures, and local Storybook environments used by AI agents.
Safety notes
Storybook's MCP server and AI manifests are preview capabilities, and Storybook states that the API may change in future releases.
The MCP server can guide an agent to generate components, write stories, preview states, and run tests. Review generated UI, stories, tests, and source changes before committing or shipping them.
Storybook docs and stories are project-controlled input. Treat component docs, story text, examples, and addon output as untrusted context that can contain stale guidance or prompt-injection-like instructions.
`run-story-tests` can execute interaction tests and browser-based component code. Do not run untrusted stories or tests with secrets, production credentials, or privileged browser sessions available.
The default MCP endpoint is local to the Storybook dev server. Do not expose the local Storybook MCP endpoint or equivalent Storybook preview URLs to networks or tunnels unless access control and data exposure have been reviewed.
When multiple Storybooks or MCP servers are configured, use descriptive server names so the model does not confuse design systems, toolsets, or component libraries.
Privacy notes
Storybook MCP tool results can expose component names, props, examples, docs, stories, design-system conventions, theme tokens, UI states, test results, accessibility findings, and story preview links.
Storybook stories and previews can contain mock customer data, screenshots, private workflows, unreleased product UI, internal brand details, or business logic visible through component examples.
Test output, accessibility reports, browser console logs, agent transcripts, screenshots, and generated summaries can retain Storybook content outside the normal repository and design-system access controls.
Composed Storybooks can aggregate documentation and stories from multiple component libraries, so verify which composed sources are exposed before connecting an agent.
Keep secrets, real user records, internal API tokens, and production credentials out of stories, play functions, test fixtures, and local Storybook environments used by AI agents.
Prerequisites
React Storybook project, because Storybook documents the MCP server and manifests as preview AI capabilities currently limited to React projects.
Node.js package manager access for installing `@storybook/addon-mcp`.
Running Storybook dev server, with the local MCP endpoint captured as `STORYBOOK_LOCAL_MCP_URL`.
MCP-compatible agent or editor that can connect to local HTTP MCP servers, such as Claude Code, Gemini CLI, OpenAI Codex, VS Code Copilot, or another compatible client.
Storybook Test, interaction tests, and accessibility checks configured if the agent should use the `run-story-tests` tool.
Project instructions such as `AGENTS.md` or `CLAUDE.md` telling the agent when to use the Storybook MCP tools and how to avoid undocumented props.
The Storybook MCP server connects Claude and other MCP-capable agents to a
running Storybook project. Once @storybook/addon-mcp is installed and the
Storybook dev server is running, the local MCP endpoint exposes toolsets for
component documentation, story authoring guidance, previews, and Storybook
tests.
This is useful when an agent is building UI inside a real design system. Instead
of hallucinating component props or copying patterns from unrelated projects,
Claude can inspect documented components, read story examples, generate or
update stories, preview UI states, and run Storybook tests or accessibility
checks when they are configured.
Features
Local HTTP MCP endpoint exposed from the Storybook dev server.
Installation through npx storybook add @storybook/addon-mcp.
Agent configuration through npx mcp-add --type http --url STORYBOOK_LOCAL_MCP_URL --scope project or manual MCP client config.
Docs toolset for listing component documentation, fetching component docs,
and reading story-specific documentation.
Development toolset for story-writing instructions and story previews.
Testing toolset for running Storybook tests and returning results, including
accessibility findings when configured.
Storybook composition support, so composed Storybooks with manifests can
expose combined component knowledge to agents.
Project-instruction guidance for telling agents to verify component props and
usage before generating UI.
Use Cases
Ask Claude to build UI using only documented components from the local
Storybook design system.
Inspect component props and examples before generating a new screen or state.
Generate or update stories that demonstrate a component or feature workflow.
Preview generated stories directly in an MCP-capable chat interface or return
links to local Storybook stories.
Run Storybook interaction tests and accessibility checks for stories touched
by an agent.
Use composed Storybooks to let an agent find components across multiple
internal design systems without copying implementation details manually.
Installation
Add the Storybook MCP addon
From the project with Storybook installed, run:
npx storybook add @storybook/addon-mcp
Start the Storybook dev server, then set STORYBOOK_LOCAL_MCP_URL to the local
MCP endpoint shown by Storybook.
STORYBOOK_LOCAL_MCP_URL
Add the MCP server to an agent
Use Storybook's documented mcp-add flow, replacing
STORYBOOK_LOCAL_MCP_URL with the local Storybook MCP endpoint:
Use the Storybook MCP server to list all documented components before generating UI.
Inspect props before coding
Get documentation for the Button and TextInput components, then build a login form using only documented props.
Generate a story
Fetch the latest Storybook story-writing instructions and create a story for the empty, loading, and error states of this component.
Preview a state
Preview the dark-mode Button story and return the Storybook link or embedded preview if supported.
Run component tests
Run Storybook tests for stories that cover the Header component and summarize failures without changing code yet.
Source notes
Storybook's official MCP docs describe the MCP server as a preview AI
capability that connects Storybook to AI agents so they can understand
components and documentation, generate stories, run tests, and reuse existing
design-system components.
The docs state that Storybook's AI capabilities, specifically manifests and
the MCP server, are currently supported for React projects and that the API
may change in future releases.
Storybook documents installation with npx storybook add @storybook/addon-mcp and a local MCP endpoint served by the Storybook dev
server.
The setup guide documents adding the local MCP server to an agent with
npx mcp-add, or manually following agent-specific MCP configuration docs.
The docs list development, docs, and testing toolsets, including
get-storybook-story-instructions, preview-stories, get-documentation,
get-documentation-for-story, list-all-documentation, and
run-story-tests.
The GitHub repository is storybookjs/mcp, is MIT licensed, and hosts the
Storybook MCP implementation.
Duplicate check
Checked current content/mcp/, content/tools/, guides, skills, agents, open
pull requests, live issue state, and repository-wide content for Storybook MCP, storybookjs/mcp, @storybook/addon-mcp,
storybook.js.org/docs/ai/mcp, STORYBOOK_LOCAL_MCP_URL, mcp-add Storybook,
list-all-documentation, get-documentation, preview-stories,
run-story-tests, and component documentation mcp. An existing slash-command
agent example mentions writing Storybook stories as a generic workflow example,
but no dedicated Storybook MCP entry, Storybook MCP source URL duplicate, or
open duplicate PR was found.
Disclosure
Editorial listing. No paid placement or affiliate link is used.
Show that Storybook MCP Server for Claude is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/storybook-mcp-server)
How it compares
Storybook MCP Server for Claude side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
1 trust signal differ across this comparison (Submitter).
Storybook MCP addon that lets Claude and other MCP clients inspect component documentation, generate stories, preview UI states, and run Storybook tests against a local Storybook project.
MCP server for extracting design systems from live websites, including design tokens, regions, components, contrast data, Tailwind themes, Figma variables, and prompt packs.
Magic MCP by 21st.dev lets Claude generate polished, production-ready UI components from natural language, returning React and Tailwind code you can drop straight into a project.
✓Storybook's MCP server and AI manifests are preview capabilities, and Storybook states that the API may change in future releases.
The MCP server can guide an agent to generate components, write stories, preview states, and run tests. Review generated UI, stories, tests, and source changes before committing or shipping them.
Storybook docs and stories are project-controlled input. Treat component docs, story text, examples, and addon output as untrusted context that can contain stale guidance or prompt-injection-like instructions.
`run-story-tests` can execute interaction tests and browser-based component code. Do not run untrusted stories or tests with secrets, production credentials, or privileged browser sessions available.
The default MCP endpoint is local to the Storybook dev server. Do not expose the local Storybook MCP endpoint or equivalent Storybook preview URLs to networks or tunnels unless access control and data exposure have been reviewed.
When multiple Storybooks or MCP servers are configured, use descriptive server names so the model does not confuse design systems, toolsets, or component libraries.
✓designlang uses Playwright to crawl live pages and can capture DOM-derived styles, responsive behavior, interaction states, screenshots, and accessibility findings.
Authenticated extraction options can use cookies, cookie files, headers, and custom user agents, so never pass production session cookies or credentials unless approved.
Generated outputs may include design tokens, Tailwind config, shadcn variables, Figma variables, component anatomy, prompts, screenshots, reports, and cloned starter code.
Commands such as apply, clone, sync, drift, visual-diff, and MCP extraction can read live websites and write files in the configured output or project directory.
Review extracted prompt packs and generated code before using them in another agent workflow or committing them.
✓The server reads Figma design data through a personal access token; use the least access practical.
Review generated UI code before merging because layout context does not guarantee accessibility, responsive behavior, or product correctness.
Do not point agents at confidential designs, unreleased product work, or customer-specific mocks unless that exposure is approved.
✓Generates UI code that is inserted into your project; review the output before committing or shipping it.
Makes outbound network requests to the 21st.dev Magic service to produce components.
Privacy notes
✓Storybook MCP tool results can expose component names, props, examples, docs, stories, design-system conventions, theme tokens, UI states, test results, accessibility findings, and story preview links.
Storybook stories and previews can contain mock customer data, screenshots, private workflows, unreleased product UI, internal brand details, or business logic visible through component examples.
Test output, accessibility reports, browser console logs, agent transcripts, screenshots, and generated summaries can retain Storybook content outside the normal repository and design-system access controls.
Composed Storybooks can aggregate documentation and stories from multiple component libraries, so verify which composed sources are exposed before connecting an agent.
Keep secrets, real user records, internal API tokens, and production credentials out of stories, play functions, test fixtures, and local Storybook environments used by AI agents.
✓URLs, page content, DOM text, CSS, screenshots, fonts, images, design tokens, cookies, headers, prompts, tool arguments, reports, and generated files may be visible to the MCP client and model provider.
Authenticated or internal sites can expose product plans, unreleased UI, customer data, analytics identifiers, private brand assets, and implementation details.
Output directories can retain extracted website data after the MCP session ends.
Avoid running the server against private, paid, internal, or authenticated properties without legal and security approval.
✓Figma file names, frame names, component names, layout metadata, styling, copy, and design tokens may be sent through the MCP server and AI client.
Figma access tokens are sensitive credentials and should stay out of prompts, screenshots, shared configs, and commits.
Design metadata can reveal product strategy, upcoming features, customer workflows, and brand assets.
✓The component descriptions and prompts you provide are sent to the 21st.dev Magic service to generate code, so avoid embedding secrets in them.
The Magic API key is a credential; store it securely and do not commit it to source control.
Prerequisites
React Storybook project, because Storybook documents the MCP server and manifests as preview AI capabilities currently limited to React projects.
Node.js package manager access for installing `@storybook/addon-mcp`.
Running Storybook dev server, with the local MCP endpoint captured as `STORYBOOK_LOCAL_MCP_URL`.
MCP-compatible agent or editor that can connect to local HTTP MCP servers, such as Claude Code, Gemini CLI, OpenAI Codex, VS Code Copilot, or another compatible client.
Node.js 20 or newer available to the MCP client runtime.
Network access to the websites you plan to extract.
Permission to crawl and analyze the target sites.
Playwright or Chromium installation behavior reviewed for the local environment.
Figma account with access to the files the agent should read.
Figma personal access token stored outside prompts and repository files.
Node.js and npx.
MCP client such as Claude Code, Cursor, or another compatible coding assistant.
Node.js 18+ and npx available (verify with: npx --version)
A 21st.dev Magic API key (create one at https://21st.dev/magic/console)
Claude Code or Claude Desktop with MCP support
Internet access so the server can reach the 21st.dev Magic service