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-design-reviewgithub.com/WawaGuess/mcp-design-reviewupdated this year
—
-
figma-design-pilot-mcpgithub.com/mr-wang007s/figma-design-pilot-mcpupdated this year
Figma Design Pilot — Stateful MCP Server for AI-powered design review and comment management
npm MIT -
kicad-mcpgithub.com/antonmadto/kicad-mcpupdated this year
MCP server to create, review, and export KiCad designs — with a Hartley/Phil's Lab design-review engine
MIT ★ 1 -
MCP server for visual regression and interactive design review.
npm SEE LICENSE IN LICENSE -
softpeach-mcpgithub.com/rashidlansah/softpeach-mcpupdated this year
MCP server that connects Claude Code to SoftPeach design review rooms
npm MIT -
Arrange live web pages on an infinite canvas and review your whole site like artboards in a design tool. macOS.
MIT ★ 1 -
Session-scoped MCP scratchpad with interactive HTML previews, revision comparison, and design review.
npm MIT -
Automated 3-layer design review and linter for KiCad (DRC/ERC, spatial heuristics, multimodal vision AI, and native MCP server)
MIT ★ 9 -
Click an element on a live page, comment, and get a markdown review a designer or coding agent can act on. One dependency-free file, plus an MCP server that hands the review to Claude Code or Cursor.
MIT -
Open-source MCP server that lets an AI drive a live session of Altium Designer, and optionally KiCad or EasyEDA Pro, editing the open design in place while you watch. 560+ tools: schematic, PCB, library and project automation, design review, audits, rendering, auto-placement, panelization, autonomous design-plan executor. Apache-2.0.
pypi Apache-2.0 ★ 369 -
@autousers/mcpgithub.com/autousers-ai/mcpupdated this year
Official MCP server for Autousers — UX evaluation, calibrated AI personas, side-by-side design review.
npm MIT -
rams-initupdated this year
Set up Rams design review for your coding agents in one command — writes the standing instruction and wires the MCP server.
npm MIT -
@grum-os/cliactive
Keep a repository on the design contract reviewed in Grum: a local drift check, review requests, Cursor hooks and an MCP server.
npm EULA -
Design Studio — Figma MCP integration, design references, RAG knowledge base, and UI/UX review for Emika AI Employees
-
MCP server for Website Feedback Tool: let Claude Code, Cursor or Codex read design reviews captured on live web pages
MIT -
motionlintgithub.com/bobaba99/motionlintupdated this year
Catch bad animations before they ship. Deterministic motion audit + vision-LLM design review for your terminal and Claude Code.
npm MIT -
MCP server that exposes a personal design system (palette generator, component rules, UI review) to AI clients
MIT -
A remote MCP server for in-loop design review, and a worked reference for OAuth 2.1 auth, SSRF-safe URL handling, and long-running jobs over MCP.
npm MIT ★ 2 -
Artemis MCP server and CLI — let Claude Code, Codex and Ares post design decisions for a human to review and hear the verdict back. Agents post and read; only people decide.
npm UNLICENSED -
A native mobile design workflow for Claude Code and Codex. SwiftUI + Jetpack Compose, reference research, design reviews and purposeful motion. Noncommercial studies.
NOASSERTION ★ 1 -
An MCP that reviews your architecture, estimates real capacity from cited numbers, surfaces the trade-offs you are making, and roasts bad design in a dry voice. Deterministic engine, no model, runs free and local.
MIT ★ 1 -
Audit any website's UX the way a design-literate reviewer would — contrast, tap targets, copy, resilience — with a concrete fix for every finding. Runs in your own Chrome; built for coding agents (MCP).
npm Apache-2.0 -
Local architecture canvas where coding agents add reviewable design steps over MCP
npm MIT -
Keep design docs in your git repo: a VitePress site people review, AGENTS.md rules and an MCP server agents use, a checker and a safe sync hook.
npm MIT -
Shared design rules for coding agents and local static/React-Vite UI checks with reviewed corrections.
Apache-2.0 -
A software factory for coding agents: product design, tech design, code and review, in one workflow.
AGPL-3.0 ★ 2 -
A Model Context Protocol (MCP) server that simulates "fake" harsh user reviews designed to tame AI agents and enforce disciplined development practices.
npm ★ 7 -
Figma design understanding for AI coding agents: extracts components, exports assets, cross-checks recognition with vision models, and scores how ready a screen is to implement. Ships an MCP server and a local review UI.
npm MIT -
UX Pilot for Cursor: find and edit your UX Pilot designs, create on-brand UI, run UX reviews and build React prototypes from Cursor, over MCP.
MIT -
Figma design understanding for AI coding agents: extracts components, exports assets, cross-checks recognition with vision models, and scores how ready a screen is to implement. Ships an MCP server and a local review UI.
npm MIT -
Mark feedback for your agent — human-in-the-loop design review over Laravel MCP
NOASSERTION ★ 3 -
Personal design-inspiration database — screenshots, palettes, and AI-written reviews of great sites/apps, searchable by Claude via MCP
MIT ★ 2 -
Drop-in client review layer for Next.js prototypes: review nav, per-page design options, and in-page comments on Supabase that Claude can read and resolve over MCP.
-
orchard-higgithub.com/sophiacave/orchard-higupdated this year
Apple Human Interface Guidelines checker for MCP. 22 HIG rules, automated design review for iOS/macOS apps.
-
A browser-based review workspace for commenting on and revising designs, documents, and code produced by AI agents
MIT -
brainregiongithub.com/fanghaoling/brainregionupdated this year
BrainRegion is an AI collaboration infrastructure designed for review, consultation, planning, and memory.
Apache-2.0 ★ 3 -
AI-powered development tools. 18 agents, 19 commands, 29 skills, 4 hooks, 1 MCP server for code review, research, design, and workflow automation.
MIT ★ 36 -
System design docs that stay in step with the system: diagrams as code (Clara DSL + Mermaid), unlimited C4 drill-down, named states, real-time collaboration, and AI edits over MCP that a human reviews. Runs on AWS (CDK).
MIT -
MCP server + Claude Code plugin for reviewing Bitbucket Cloud pull requests without cloning. Default-deny repo allowlist, separated write gates, no approve/merge tool by design.
MIT -
HARNESS-DB: 1,256 LLM agent harnesses coded on 38 design dimensions with a verbatim quote behind every value; pre-registered PRISMA 2020 review; loader, explorer, MCP server
MIT ★ 3 -
dotnetcodereviewer.mcpserverupdated this year
An MCP (Model Context Protocol) server that performs deep static code review of C#/.NET source using Roslyn. Plugs into AI coding tools such as Claude, Cursor, and Cline to review code for bugs, security issues, performance problems, and design smells.
nuget MIT -
A local-first bridge that enables coding agents to turn Figma designs into code and create safe, reviewable design proposals in Figma.
npm MIT ★ 3 -
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 -
contentrx-mcpgithub.com/thenewforktimes/contentrxupdated this year
ContentRX MCP server — content-design review for Claude Code, Cursor, and any MCP client.
pypi MIT -
WeChat article exports for Agents: Markdown, PDF, reviewed ad removal and statistics. Designed By MOTAN.
MIT ★ 3 -
Diagrams.sono update data
Generate and edit cloud architecture diagrams from an AI agent or your own code. Native draw.io output, 30+ cloud icon packs, built-in design review.
smithery -
MCP server for hypothesis-driven data analysis — manage analysis designs, data catalogs, and review workflows
pypi MIT -
Editable scientific figures in PowerPoint and draw.io via Codex/MCP with Designer-Drawer-Reviewer-Corrector quality gates.
MIT ★ 1,000 -
Find out why a component exists and what changes if a decision went the other way. Reads the ADRs, RFCs and design notes already in your repo, cites the passage behind every inferred claim, keeps human review on top, and previews option switches on a map. Local-first, Markdown only, MCP tools for agents.
Apache-2.0 -
@automyc/studioactive
Automyc studio: a local MCP server that renders, edits and reviews video and designs on your own computer for Claude Code, Codex and other AI apps.
npm UNLICENSED -
Claude Code plugin for the Basirah enterprise survey platform — survey search, privacy-safe aggregate analytics, suppressed crosstabs, design validation, and review-gated drafting over MCP
MIT -
Draw.AI: chat with AI to edit draw.io diagrams live in VS Code (review mode, markup, sketch/code to diagram, design templates, MCP). Unofficial fork of hediet/vscode-drawio.
GPL-3.0 -
Chain of Draft Server is a powerful AI-driven tool that helps developers make better decisions through systematic, iterative refinement of thoughts and designs. It integrates seamlessly with popular AI agents and provides a structured approach to reasoning, API design, architecture decisions, code reviews, and implementation planning.
MIT ★ 24 -
AI YouTube thumbnail generator for Claude: skills + MCP server to design, score and revise thumbnails. Free thumbnail review included.
MIT -
Parse and analyze KiCad PCB files from AI agents. Layer stackup, net listing, footprint inventory, DRC violation surfacing, board outline geometry. Built for design review automation and pre-fab sanity checks.
go MIT -
Devsquadgithub.com/abhaybansal0322/Devsquadupdated this year
Published MCP server that turns vague coding prompts into gated, role-based workflows for AI coding agents — prompt classification, three execution paths, and rule-based review gates. Zero shell access by design.
-
MCP server for Bitbucket Cloud focused on AI pull request review. Dual stdio/HTTP transports, OAuth or bearer auth, and tools to list, create, diff, comment, and analyze PRs. Pluggable LLM (OpenAI, Anthropic, Gemini, Bedrock) and provider-agnostic design for other SCMs.
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 -
Self-hosted team knowledge base for Claude and other MCP clients: shared project, design and tech knowledge with human review, semantic search and cross-project sharing.
MIT ★ 5 -
Workflow-level MCP server for Vikunja: a gated Backlog→Queue→Design→Build→Review pipeline that AI coding agents can be left alone with. Agents can never move a task to Done.
MIT ★ 4