MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
MCP Agent focused on providing mock System Design Interview
-
MCP server for Website Feedback Tool: let Claude Code, Cursor or Codex read design reviews captured on live web pages
MIT -
handle-extgithub.com/tonkotsu-ai/handleupdated this year
Design feedback bridge between Handle's Chrome extension and AI coding agents via MCP
npm MIT -
Mark feedback for your agent — human-in-the-loop design review over Laravel MCP
NOASSERTION ★ 3 -
Personal brand-taste memory for Claude Code: capture liked designs → local MCP sidecar → /design generates frontends in your accumulated taste. Brand-scoped cases, aspectual feedback, NEVER rules, approval-gated distillation.
MIT ★ 8 -
design-modegithub.com/harshkedia177/design-modeupdated this year
Point at your UI. Tell Claude what to change. Watch it happen. Visual overlay for annotating and inspecting UI elements — Claude applies your design feedback directly to source code.
npm ★ 8 -
A powerful, open-source Model Context Protocol (MCP) server for automated, multi-language code feedback, validation, and project analysis. Designed for developers, teams, and LLM-powered workflows to ensure code quality, correctness, and maintainability across diverse languages and build systems.
npm MIT ★ 1 -
Your clients' corporate design in one place, self-hosted: colours, fonts, logos and every version, with contrast checks, an API and MCP. Early days, ideas and feedback welcome.
AGPL-3.0 ★ 2 -
@layernote/mcpactive
MCP server that gives Claude and other AI agents a layernote project's feedback: comments on live sites, designs and uploaded files
npm MIT -
Hand-drawn whiteboard for system design mock interviews — an MCP server that lets Claude or ChatGPT watch your board, talk with you, and give feedback.
npm MIT ★ 1 -
Model Context Protocol server for visual feedback and UI testing automation. Take screenshots, compare against reference designs, and get actionable feedback to help coding agents iterate faster on UI development.
MIT -
woku AI Toolkit: connect your agent to woku's voice-of-customer platform. Design VoC programs and turn customer feedback into support tickets and action plans, through woku's MCP server.
npm MIT -
Design and operate a Store Builder site from an AI agent — pages, data, live editing and a screenshot feedback loop, over MCP.
npm MIT ★ 1 -
A Model Context Protocol server providing LLM Agents a second opinion via AI-powered Deepseek-Reasoning R1 mentorship capabilities, including code review, design critique, writing feedback, and idea brainstorming through the Deepseek API.
Apache-2.0 ★ 32 -
imgui-mcpgithub.com/SaloQT/imgui-mcpupdated this year
Dear ImGui MCP Server — AI agents design, control & debug game UIs in real-time. 70+ tools, 102 widget types, visual feedback, animation, export. Works with Claude, Cursor, VS Code, omp, Windsurf, Zed, Gemini CLI & more.
MIT ★ 7 -
Self-hosted UI feedback: anchored comments, screenshots, a Shadow DOM SDK and MCP.
MIT -
MCP server for visual regression and interactive design review.
npm SEE LICENSE IN LICENSE -
An MCP server that lets Claude read your Figma comments and Dev Mode annotations. Read-only, scoped to the frame you link.
ISC ★ 4 -
@perpetio/redlineactive
A review layer for any website, built for coding agents. Reviewers comment on the live page; Claude Code, Codex or Cursor reads each comment over MCP with the exact element, fixes it and resolves it. One script tag, no dependencies.
npm SEE LICENSE IN LICENSE -
Claude Code plugin for Deixis, the Mac app for screenshot feedback: point, say or type what should change, and the round arrives in your session.
MIT -
Talk through a web page while you draw on it. Your coding agent gets the feedback: transcript + marked elements + screenshots, via CLI, MCP or Chrome extension.
MIT ★ 1 -
Open-source, free webpage annotator with real-time collaboration. Share a link, no account needed. AI agents work the feedback over MCP.
npm Apache-2.0 ★ 54 -
@pallandir/northstargithub.com/pallandir/northstarupdated this year
MCP server that ingests real-time UI comments from the Northstar extension and exposes them to an AI coding assistant.
npm PolyForm-Noncommercial-1.0.0 -
A small shared store for Redline notes: projects, personal tokens, MCP per project and a web UI, in one SQLite file. Localhost by default.
npm MIT -
AI-native web production platform — sitemap, content drafts and visual review unified around pages. MCP-first, Cloudflare-native (Workers+D1+R2). AGPL-3.0
AGPL-3.0 -
critlab CLI + MCP server: feedback on prototypes built with AI agents
npm UNLICENSED -
@mcardoso.dev/regua-mcpactive
Entrega a um agente de código (Claude Code, Cursor e outros clientes MCP) os comentários e ajustes deixados com a Régua, e devolve à página o que ele fez
npm MIT -
MCP server for precise visual component comparison and constructive feedback
npm MIT -
@atc-group/ui-annotator-2updated this year
MCP server that annotates any web page with hover labels — zero extensions, any browser. Fixed proxy encoding and asset routing.
npm MIT -
A review session your agent can join. Share a build at a stable URL; reviewers click the element they mean; an agent reads the source behind it, resizes their preview, and replies in the thread — over WebMCP, MCP and a JSON CLI.
npm MIT -
MCP server for precise visual component comparison, alignment analysis, color comparison, border analysis, and constructive feedback
npm MIT -
FeedbackPulse plugins for Claude, Cursor and Grok. Design employee engagement, pulse and eNPS surveys, and read survey results, eNPS and review progress.
MIT -
Local, click-to-comment visual review for HTML you're still building — Claude Code publishes a block to a local review server, you click an element and leave feedback, Claude reads it back anchored by a screenshot.
npm MIT -
Self-hosted artifact server for AI agents: Claude Code, Cursor and Codex publish HTML pages over MCP, you review them with pinned comments, versions and share links, and the agent reads your feedback and fixes them.
Apache-2.0 ★ 7