It provides a connection for using Claude Design from an agent instead of handling the project manually in the browser.

claude-design — MCP server by e-brokenc0de/claude-design-mcp

claude-design

claude-design is an MCP server for Claude Code from e-brokenc0de/claude-design-mcp. Its token cost is not measured, scanned A, original, MIT.

An MCP server, which lets an agent connect to the Claude Design project through configured local software and a logged-in browser session.

In plain words

What is it for?: Use it when an agent needs to work with Claude Design projects, such as creating, inspecting, changing, or exporting design work.
Why use it?: It provides a connection for using Claude Design from an agent instead of handling the project manually in the browser.

Written for Claude Code: ${CLAUDE_PROJECT_DIR variable. Also seen: listed in a Claude config.

Good fit Use it when an agent needs to work with Claude Design projects, such as creating, inspecting, changing, or exporting design work.

Compare 6 mcp servers from other repositories ↓

Install with agentmods

npx agentmods add mcp/e-brokenc0de/claude-design-mcp/claude-design

Installing this writes the configuration, not the program: `node` runs a file from the repository, so clone it first and make the path in the command match where you put it.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/e-brokenc0de/claude-design-mcp

Installing this writes the configuration, not the program: `node` runs a file from the repository, so clone it first and make the path in the command match where you put it.

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/e-brokenc0de/claude-design-mcp/claude-design/github.svg)](https://agentmods.dev/mcp/e-brokenc0de/claude-design-mcp/claude-design)

Your own site

<a href="https://agentmods.dev/mcp/e-brokenc0de/claude-design-mcp/claude-design"><img src="https://agentmods.dev/badge/mcp/e-brokenc0de/claude-design-mcp/claude-design/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/mcp/e-brokenc0de/claude-design-mcp/claude-design"><img src="https://agentmods.dev/badge/mcp/e-brokenc0de/claude-design-mcp/claude-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

claude-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.mcp.json · 15 lines

What it actually says

{
  "claude-design": {
    "type": "stdio",
    "command": "node",
    "args": [
      "${CLAUDE_PROJECT_DIR:-.}/dist/server.js"
    ],
    "env": {
      "CLAUDE_DESIGN_CDP_PORT": "9222",
      "CLAUDE_DESIGN_CDP_USER_DATA_DIR": "${CLAUDE_PROJECT_DIR:-.}/.auth/cdp-chrome",
      "CLAUDE_DESIGN_STATE_DIR": "${CLAUDE_PROJECT_DIR:-.}/.claude-design-mcp"
    },
    "timeout": 600000
  }
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 15 lines scan A eb755de7d078

Subscribe to this mod's changes

claude-design is an MCP server published in the GitHub repository e-brokenc0de/claude-design-mcp (0 stars, last pushed 5mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Design and UX anthropic claude design-system design-tokens mcp

claude-design next to 6 mcp servers from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
claude-designe-brokenc0de/claude-design-mcp	MCP server	0	5mo ago	MIT	A	—	Claude Code
design-dataadobe/spectrum-design-data	MCP server	159	yesterday	Apache-2.0	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
figmaadobe/spectrum-design-data	MCP server	159	yesterday	Apache-2.0	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
figbridgerudraptpsingh/figbridge	MCP server	15	28d ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
mimic-aimiapre/mimic-ai	MCP server	15	29d ago	MIT	A	—	Claude Code, Codex, Cursor, Gemini CLI, OpenCode
figma-mcp-bridgeatezer/FMCP	MCP server	10	23d ago	MIT	A	—	Claude Code
uisandboxIdeelab/uisandbox	MCP server	7	16d ago	MIT	A	—	Claude Code