1. Conduid
  2. Developer Tools
  3. mcp
MCP server · Developer Tools

mcp

by · github.com/EvanZhouDev/viewlint

Find UI issues on live websites.

Unclaimed ailintmcpui
InstallView source
39Low

Scored 17 days ago · breakdown

About mcp

mcp is an MCP server published by git+EvanZhouDev in the Developer Tools category: find UI issues on live websites.

The repository has 5 stars and 0 forks.

Install

Install
npx @viewlint/mcp
Claude Code
claude mcp add viewlint -- npx -y @viewlint/mcp
npx
npx -y @viewlint/mcp

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about mcp

Powered by Claude · Grounded in docs

I know everything about mcp. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ✓README presentThe repository ships documentation.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

4 checks have not been run yet.

README

Documentation | NPM

ViewLint helps identify UI issues by analyzing the rendered output a human sees, not just source code.

Built for modern coding workflows and AI Agents, ViewLint accelerates workflows from development to shipping. It's designed to be ready to use out-of-the-box and extensible when you need it, making it perfect for individual developers to enterprise organizations.

ViewLint visualized

Quick Start

Initialize ViewLint:

npm init @viewlint/config@latest

Run it on a URL:

npx viewlint https://example.com

For setup details and advanced configuration, see the Getting Started guide.

The UI Linting Problem

UI issues such as clipped content, overflow, low contrast, and obscured hit targets are often hard to catch from source code alone.

Instead, ViewLint validates your UI the same way a human does, looking at and interacting with the actual rendered browser output to catch potential issues.

UI's Broken Feedback Loop

LLMs are fantastic at writing code. They're not so great at making UI.

As it turns out, that's because Coding Agents have a closed feedback loop to validate their code and logic. But when it comes to UI, inspecting the DOM tree manually and taking screenshots just aren't concrete and actionable enough to close that feedback loop.

Broken feedback loop

ViewLint closes the feedback loop with UI design, allowing the agent to get live, actionable feedback on the rendered output of the website it's working on.

Broken feedback loop

ViewLint significantly improves the UI design performance of AI Agents. Learn more and see the difference at the ViewLint documentation.

Documentation

Get started exploring ViewLint and add it to your project with the ViewLint documentation at viewlint.vercel.app.

Repo Structure

ViewLint is a monorepo, hosting a series of packages in the ViewLint ecosystem as well as the documentation site.

  • apps/
  • packages/
    • viewlint/: Core ViewLint package and CLI (viewlint on NPM)
    • rules/: Core ViewLint rules (@viewlint/rules on NPM)
    • create-config/: ViewLint config initializer (@viewlint/create-config on NPM)
    • mcp/: ViewLint MCP server (@viewlint/mcp on NPM)
    • typescript-config/: Shared TS config for monorepo

License

AGPL-3.0-only

README copy captured when this server was indexed; it may lag the repository. The original is authoritative.

Questions

About mcp

How do I install mcp?

Run npx @viewlint/mcp, then add the server to your MCP client's configuration.

Is mcp safe to use with an AI agent?

Its trust score is 39 out of 100 (low). It passes 1 of the 2 static security checks run so far; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is mcp still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.