A local bridge that lets a coding agent communicate with the Open Design service, a tool for working with UI design systems. It requires the Open Design service to be running on the local computer, and design generation also needs a user-provided API key.

Use it to read, list, create, inspect, lint, or generate designs through a locally running Open Design service.

It connects the agent to the design service so it can use its design-system tools without manually switching between systems.

open-design — MCP server by HelixDevelopment

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.

agentmods

npx agentmods add mcp/helixdevelopment/code/open-design

Clone the repo

git clone --depth 1 https://github.com/HelixDevelopment/code

Made for: Claude Code, Codex, Cursor.

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. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

open-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 yesterday.

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 · 16 lines

What it actually says

{
  "open-design": {
    "description": "OpenDesign MCP server for UI design system (§11.4.162). Bridges the agent to the OpenDesign daemon (nexu-io/open-design) on localhost:7456. Start the daemon first: `node apps/daemon/dist/cli.js --port 7456 --no-open` from a from-source checkout, or the desktop app / `docker compose up` in deploy/ (fixed :7456). od_generate_design additionally needs operator BYOK env (HELIX_OD_BYOK_* in .env, §11.4.10) — the read/list/create/get/lint tools do not.",
    "type": "stdio",
    "command": "npx",
    "args": [
      "-y",
      "open-design-mcp"
    ],
    "env": {
      "OD_DAEMON_URL": "http://localhost:7456"
    },
    "disabled": false,
    "autoApprove": []
  }
}

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.

yesterday First seen · 16 lines scan A f9357e8a60ba

Subscribe to this mod's changes

open-design is an MCP server published in the GitHub repository HelixDevelopment/code (2 stars, last pushed 4d 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.

Backend and APIs Code review Frontend agent agentic-ai agents ai ai-agents cli

open-design

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other mcp servers, from other repositories

nx-mcp

copilotkit-docs

nightgate-mcp

1stay

docs-langchain

reference-langchain