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 server for visual regression and interactive design review.
npm SEE LICENSE IN LICENSE -
ai-diff-review-mcpgithub.com/iiNothh/ai-diff-review-mcpupdated this year
An open-source, advanced difference viewer MCP for Visual Studio Code-based AI editors. - Download: https://marketplace.visualstudio.com/items?itemName=DifferenceMCP.ai-diff-review-mcp
MIT ★ 1 -
mcp-component-reviewgithub.com/igorvieira/mcp-component-reviewupdated this year
MCP server for reviewing React component changes with visual diffs and Figma validation
MIT -
An MCP server that performs a visual review of UI edit requests
npm MIT -
Agent-initiated review: a shared browser window where humans annotate git diffs, files and visual drafts, organised in review rounds, read back over MCP.
npm MIT -
In-browser visual editing, annotation, and review overlay for AI coding agents via MCP
npm MIT ★ 5 -
Visual review for local and Cloudflare preview deploys. Compare DEV against LIVE with split, overlay/diff, synced navigation, response deltas, and SEO checks, plus a Pages addon and an MCP interface.
npm MIT ★ 4 -
eda-reviewgithub.com/JonathanLiu1401/eda-reviewupdated this year
AI-assisted EDA review for KiCad and Altium: schematic/layout understanding, BOM sourcing, JLCPCB DFM checks, fab exports, ERC/DRC, and visual review workflows.
MIT ★ 2 -
@sitepager/mcp-serveractive
MCP server for Sitepager, enabling repeatable website review workflows for visual changes, broken links, SEO metadata, and performance checks before updates go live.
npm SEE LICENSE IN LICENSE -
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 -
Markdown → reviewed slide plan → on-brand slide visuals. MCP server for Claude Code with approval gates and pluggable visual systems
MIT ★ 1 -
dev.dungbeetle/mcpgithub.com/dungbeetletech/cloudno update data
Visual regression & snapshot testing for AI agents — list runs, read semantic diffs, review.
npm -
Review what Claude Code is about to change on a rich visual surface — inline comments, evidence, and a gate that remembers the approaches you rejected.
MIT ★ 1 -
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 -
Understand what your codebase builds, why it is structured that way, and what a change could affect. One shared Markdown ontology for humans and coding agents—visualized for people, accessible to agents through MCP, and reviewed with Git. Local-first. Open source.
mcpb MIT ★ 157 -
MCP server for Blender: model, light, render, animate and export from any agent, with visual review. Signed local bridge, CC0 assets.
MIT -
Open-source SSH/SFTP client and visual Linux VPS manager for macOS and Windows, with reviewed website deployments and local MCP.
MIT -
Local CLI and MCP tools for experimental load-path analysis of 3D-printed STL parts, CAD revision comparisons, visual reviews, and human-guided engineering sessions.
MIT -
AI digital painting for Adobe Photoshop — autonomous agent workflow with scene planning, visual review, iterative correction, brush-based execution and MCP integration.
MIT ★ 1 -
Open-source pixel-art engine for AI agents. Editable sprites, eight-direction animation, and visual review through MCP, CLI, and JavaScript.
MIT ★ 3 -
Local MCP server for writing consistent serial fiction with continuity checks and approval workflows, then adapting chapters into webtoon scenes: one image per scene with dialogue in the work language, pre-generation checks and visual review.
npm Apache-2.0 -
👁️ /screenshot — real Chrome screenshots for your coding agent. A Claude Code plugin: 3 skills, a visual-reviewer agent and a bundled MCP camera.
MIT ★ 1 -
Agentic-BIM-Compliancegithub.com/Prajwalkadam29/Agentic-BIM-Complianceupdated this year
This project replaces error-prone, 2-day manual structural reviews with a 4-minute Agentic AI workflow that parses IFC models for code compliance. It ensures structural safety through real-time 3D visual overlays, explainable reports, and automated "auto-fix" design suggestions.
MIT ★ 1 -
DreamLayer image toolsno update data
Generate and edit images, remove backgrounds, upscale, and create reference-based sprite animations inside agent workflows. DreamLayer gives coding agents image tools through MCP, CLI and API. Generate visual assets, edit a supplied reference, remove backgrounds or upscale; use task workflows for logo and app-icon concepts, ecommerce imagery, print artwork, marketing variations and bounded photo batches. The sprite beta creates a downloadable animation ZIP from a reference image, with examples for Godot and Unity. Workflows check capabilities and balance, keep generation within an approved credit budget, recover existing jobs and download outputs into your project. **Setup:** this is a local stdio server (Node 22.12 or later). Configure it with a DreamLayer API key from platform.dreamlayer.io; `api.dreamlayer.io` is a REST endpoint, not a remote MCP URL. **Limits:** paid API credits; sprite generation is beta with frame-based pricing; standard operations currently cost one credit per image, but always read live capabilities. Logo concepts are raster with no vector output or trademark clearance. Print artwork needs resolution, alpha and print-spec review. Product details can drift during generative edits. No guarantee of rankings, installs, brand consistency or production-ready animation. Source and skills: https://github.com/TheDesignFounder/dreamlayer-agent-plugin · Runtime: https://github.com/TheDesignFounder/dreamlayer-mcp · Privacy: https://dreamlayer.io/privacy
smithery -
Local-first Visual Direction Loop: point at visible targets, deliver a versioned Visual Intent Envelope over MCP, verify by hand.
npm Apache-2.0 -
Your codebase companion for JavaScript/TypeScript, in the browser, the terminal and your AI agent: a live dependency map, impact and call sites, affected tests and patch coverage, review order, new-only CI gates (SARIF, GitLab), git hooks, a status line a
npm MIT -
Pin visual feedback on any live web page and send it to Claude Code, Cursor or your AI agent.
npm Apache-2.0 ★ 2 -
读取你的麦当劳订单,生成麦门八型人格年度报告海报 - 麦当劳 MCP 大赛参赛作品
MIT -
Self-hosted UI review for code, copy, and rendered screens. Get weighted 0-100 findings for usability, craft, accessibility, and writing through a CLI or MCP server.
-
Self-hosted UI feedback: anchored comments, screenshots, a Shadow DOM SDK and MCP.
MIT -
VisionQA:宿主智能体(Chrome / MCP / 桌面)的视觉评审插件,截图 + DOM 证据 → 可追溯评审;默认离线 Mock,真实多模态 Provider 需本地显式启用
-
A Python toolkit — AI for Science
AGPL-3.0 ★ 85 -
@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 -
CodeRef-AI:Vibe Coding 项目的治理外脑 | 安全、健康、变更守护平台 CodeRef AI: The Governance External Brain for Vibe Coding Projects | Security, Health, Change Guard Platform
NOASSERTION ★ 4 -
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 -
See every screen of your web app as the code renders it, compare it with live, and send changes back to your coding agents.
MIT ★ 17 -
annotaskgithub.com/kurtstohrer/annotaskupdated this year
Annotate the UI of your running web app. AI agents apply the changes back to source. Dev-only Vite + Webpack plugin with MCP, CLI, and HTTP surfaces.
MIT ★ 3 -
PaperPlotHubgithub.com/Trae1ounG/PaperPlotHubupdated this year
面向全球研究人员的开源论文绘图脚本市场 | Open, AI-reviewed marketplace of academic paper plotting scripts for global researchers
MIT ★ 73 -
StoryShelf MCP server: let AI agents read builds, diffs and AI insights, and comment on reviews.
npm MIT -
Renders what a branch changed to your architecture as one picture a human can confirm at a glance, and gives a coding agent boundary verdicts it can run on itself before asking for review. Hexagonal / ports-and-adapters, Kotlin. CLI · MCP · web UI.
MIT -
prefxplaingithub.com/prefoptimize/prefxplainupdated this year
Explain your codebase in 30 seconds. Interactive architecture diagrams with AI descriptions, health scoring, and blast radius analysis. Works with Claude Code, Codex, Copilot CLI, and Gemini CLI.
pypi MIT -
@thedesignagent/mcpactive
MCP server and CLI for TheDesignAgent — UX and visual judgment layer for agent-generated UI
npm MIT -
Finds the bugs between your frontend and backend, and between your code and your database. Reads Django, FastAPI, Flask, Express, Fastify, NestJS, Next.js, plus Supabase, Firebase and Redis. Four verdicts, one of which is "I don't know".
MIT ★ 1 -
NLP research assistant over arXiv: NMF topic modeling, LLM-based findings extraction, trend analysis, and cited literature reviews. Interactive live demo.
-
🔎 Username, email & phone OSINT — 9,700+ lookup checks from 19 projects, with profile enrichment, bulk searches, evidence graphs and expert-reviewed updates.
pypi GPL-3.0 ★ 272 -
Local-first MCP App for scientific figures. Import, review, and publish a global library on disk; reuse exact templates in Pi, DeepSeek Harness (dsh), Claude, Codex, Cursor, and Wisp.
npm MIT ★ 140 -
Local dashboard + stdio MCP server: a real-time module dependency graph (test status / type errors / AI-review at a glance) that gives coding agents structural trust — 浏览器实时依赖图,给编码 Agent 一部显微镜。100% local, zero remote calls.
MIT ★ 1 -
Open exoplanet observatory: searches public TESS light curves for transit dips, has every candidate reviewed by AI Sentinels and deterministic Probes, and explains every verdict. Frozen real-TOI benchmark, public leaderboard, 3D galaxy of every known exoplanet, MCP server. Candidates, never claims.
pypi AGPL-3.0