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. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist), and packages the registry no longer has are removed. 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.
-
Lastest Visual Regression Testing - Cloud/Self-hosted version
npm NOASSERTION ★ 22 -
UI Visual Comparison Testing tool - visual regression testing tool based on Playwright
npm MIT -
MCP server for visual regression and interactive design review.
npm SEE LICENSE IN LICENSE -
@fudzuki/uishot-mcpactive
Screenshot-based page catalog & visual regression MCP server (Playwright driver)
npm SEE LICENSE IN LICENSE -
MCP server exposing TestivAI visual regression results to AI coding agents
npm MIT -
Visual regression testing by comparing two URLs side by side
npm MIT ★ 1 -
@iflow-mcp/hassan-alnator-eyes-mcp-servergithub.com/hassan-alnator/eyes-mcp-serverupdated this year
MCP server for automated testing with visual regression and OCR
npm MIT -
MCP server that teaches AI coding assistants how to author visual/screenshot regression tests for the storybook-addon-playwright Storybook addon
npm MIT -
@thepixelhouse/cligithub.com/togglekit/the-pixel-houseupdated this year
Visual regression testing CLI for The Pixel House. Capture screenshots, diff them, manage baselines, run monitors, and serve a local MCP server for AI coding assistants.
npm MIT -
@sitelensapi/mcpactive
SiteLens MCP and CLI for browser automation, observability, diagnostics, visual regression, website capture, and named target extraction. Optional Cloud/API. No Docker required.
npm UNLICENSED -
snapdrive-iosgithub.com/MasamiYamate/snapdrive-iosupdated this year
AI agents drive iOS Simulator to generate snapshot baselines and run visual regression tests.
MIT ★ 1 -
MCP server for frontend UI debugging — component inspection, visual regression, a11y auditing, and session replay via CDP
npm MIT -
@heinrichb/web-suitegithub.com/heinrichb/web-suiteupdated this year
Config-driven Playwright + visual-regression harness for any website. Route-catalog discovery, reusable check primitives (a11y, broken-links, perf-budget, computed-style, visual-baseline), flow runner, edge-case generators, CLI, MCP server. Target-agnosti
npm MIT -
Saccadegithub.com/tavrin/saccadeno update data
Perceptual visual regression, image evidence inspection and bounded decision proposals.
cargo -
Enhanced Cua distribution with African sandbox profiles, MCP server, benchmark regression detection, and architecture visualization
MIT -
superbasedgithub.com/marmutapp/superbasedupdated this year
Screenshot capture, AI analysis, OCR, visual regression testing, token compression — headless server + MCP tools for AI coding CLIs
npm ISC -
dev.dungbeetle/mcpgithub.com/dungbeetletech/cloudno update data
Visual regression & snapshot testing for AI agents — list runs, read semantic diffs, review.
npm -
superbased-cursor-plugingithub.com/marmutapp/superbased-cursor-pluginupdated this year
SuperBased plugin for Cursor — screenshot capture, AI vision, OCR, screen recording, visual regression testing, token compression, voice dictation, and proactive monitoring via 28 MCP tools
-
superbased-codex-plugingithub.com/marmutapp/superbased-codex-pluginupdated this year
SuperBased plugin for OpenAI Codex — screenshot capture, AI vision, OCR, screen recording, visual regression testing, token compression, voice dictation, and proactive monitoring via 28 MCP tools
★ 1 -
superbased-copilot-plugingithub.com/marmutapp/superbased-copilot-pluginupdated this year
SuperBased plugin for GitHub Copilot CLI — screenshot capture, AI vision, OCR, screen recording, visual regression testing, token compression, voice dictation, and proactive monitoring via 28 MCP tools
-
MCP bridge that gives Claude the eyes of a Minecraft player: studio screenshots, entity framing, inventory and lore reading, visual regression detection. Fabric client mod + MCP server.
NOASSERTION -
SuperBased plugin for Claude Code — screenshot capture, AI vision, OCR, screen recording, visual regression testing, token compression, voice dictation, and proactive monitoring via 28 MCP tools
★ 1 -
layout-lint-mcpgithub.com/LOsioChico/layout-lint-mcpupdated this year
MCP server that detects visual layout bugs via deterministic DOM analysis — overflow, spacing, typography, touch targets, responsive regressions
MIT ★ 2 -
eagleeye-mcpgithub.com/baimaomaomao556/eagleeye-mcpupdated this year
EagleEye MCP — pixel-accurate visual toolbox for Agents (screenshot, measure, OCR, regression)
MIT -
Claude plugins and skills for Visual Sentinel monitoring (uptime, performance, SSL, DNS, visual regression, content change). Marketplace bundles MCP server + skills + slash commands.
MIT -
Terminal automation for AI agents: PTY sessions, image-aware screenshots, visual regression, recording/replay, and MCP.
MIT ★ 1 -
Cornea: deterministic visual inspection engine + MCP server. Lets an AI agent 'see' the pages it built as token-cheap geometry (overlap, overflow, contrast, regression, responsive) instead of pixel dumps. No Chromium dependency.
MIT ★ 1 -
screentest-mcpgithub.com/marilynceo/screentest-mcpupdated this year
Visual testing for AI agents u2014 screenshot capture, pixel-perfect diff, baseline management, element detection, layout analysis. 7 tools: capture_screenshot, compare_screenshots, set_baseline, check_regression, detect_elements, analyze_layout, batch_test.
-
Enhanced tscircuit distribution with MCP server for AI agents, AI-assisted design tools, DFM/DRC analysis suite, African hardware domain components, interactive architecture visualization, benchmark regression detection, and comprehensive documentation
NOASSERTION -
🧠 Local-first LLM state branching & debugging. Capture, visualize, branch, and regression-test LLM calls as a DAG. Free & local via Ollama, any OpenAI-compatible API, MCP for agents. Zero config.
npm MIT ★ 3 -
@mobilepixel/mcpgithub.com/mrtrotskiy/mobilepixelupdated this year
AI-powered MCP server for mobile testing: 20 free tools for iOS & Android automation via Claude/Cursor. Natural language commands, Appium-based, npx ready. Pro adds OCR, visual regression, parallel execution.
npm Apache-2.0 -
Standalone MCP server for SnapDiff
npm MIT ★ 5 -
difflens-cligithub.com/byzkhan/difflensupdated this year
MCP server that gives AI coding agents visual diff capabilities for UI work
npm MIT -
ui-compare-mcpupdated this year
UI图片精准对比MCP服务 - 基于算法的像素级差异检测
npm MIT -
@applitools/mcpactive
Applitools MCP server for AI coding assistants
npm SEE LICENSE IN LICENSE -
MCP server for visual QA: SSIM screenshot diffs for AI-driven refactoring, with OAuth/session support for apps
MIT ★ 1 -
@logicsync/pixelprobegithub.com/logicsync/pixelprobeupdated this year
Responsive visual & style diff for web page sections — CLI + MCP
npm MIT -
MCP server for smart visual testing of web apps — frame capture, diffing, and interaction replay
npm MIT -
VFA — Visual & Functional Auditor: auditoria web autonoma (visual + funcional) expuesta como servidor MCP, con Playwright local y motor universal LiteLLM.
pypi LicenseRef-Proprietary -
Expose independently supplied observability evidence to an MCP client.
npm MIT -
Prove that what already worked still works after an agent changed the code. Picture checks, guards for fixed bugs, a pre-release walkthrough and known-good markers — as a CLI and as an MCP server.
npm MIT -
@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 -
DiffiCat clients: CLI, GitHub Action, Claude Code plugin and MCP setup
npm MIT -
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 -
The visual verifier for agentic coding workflows — deterministic-first UI screenshot diffing (DOM+pixel), tiered descriptions, CLI, MCP server, GitHub Action
npm MIT -
page_to_pagegithub.com/alexeymoskalev-devops/page_to_pageupdated this year
MCP server for Angular → Next.js visual migration: walks every page, pixel-diffs across mobile/tablet/desktop viewports, and tracks resumable progress. Published as @noders/page-to-page.
-
@visualq/mcpgithub.com/abecms/visualq-mcpupdated this year
MCP server for VisualQ — qa profile (44 tools): run_full_audit, VRT/FRT, tracking proof, investigation ladder, rolling health
npm MIT -
la-forge-mcpgithub.com/MonomythDevelopment/la-forge-mcpupdated this year
Visual CSS debugging for AI coding assistants — an MCP server for pixel-perfect screenshot comparison, computed-style extraction, and CSS rule-chain analysis.
MIT ★ 1 -
smart-ui-validator-mcpupdated this year
Approval-gated stdio MCP server for Smart UI inspection, deterministic validation, bounded repair, reports, and governed memory.
npm MIT -
Compare Figma designs and prototype flows against your running web or React Native app, and get a parity report. Works headless (Playwright/Appium) or through Claude via MCP.
npm MIT -
Deterministic UI-vs-Figma validation MCP server (layout, screenshots, accessibility) over STDIO
npm MIT -
normascope-mcpactive
MCP server giving coding agents eyes: capture a running UI, compare it against a mock or design source, read structured results.
npm Apache-2.0 -
imugigithub.com/M00N7682/imugiupdated this year
Give AI eyes to see your frontend. Design → pixel-perfect code with visual verification. MCP server for Claude Code & Cursor.
MIT ★ 12 -
codeloop-mcpgithub.com/OrienjoJi/codeloop-mcpupdated this year
CodeLoop — automated verification, self-repair, and confidence gating for AI coding agents (Cursor, Claude Code). Build → Verify → Diagnose → Fix → 94% gate.
NOASSERTION -
Validate AI-built front-ends against their Figma design — deterministic token + geometry conformance, not pixels. MCP server + Claude Code skill.
npm MIT ★ 8 -
Render testing built for AI agents: a map of the screen instead of screenshots, actions by intent, map-to-map comparison. MCP server and library. Verified by Healer.
MIT -
@mdvp/cligithub.com/tixo-digital/mdvp-cliupdated this year
Design linter for AI-generated frontends: deterministic rendered-DOM audits, CI gates, and MCP design-quality signals
npm MIT -
lucross-sensory-grounding-mcpgithub.com/luclinocruz/lucross-sensory-grounding-mcpupdated this year
Give Claude Code / Codex / any MCP agent real eyes and ears — closed-loop visual/audio/video verification with mandatory enforcement hooks, so agents stop reporting 'done' when it isn't.
Apache-2.0 -
AI-callable test automation as an MCP server: generate, run, triage and heal tests (Playwright/pytest) from any MCP-compatible AI agent.
MIT -
Give your AI agent eyes (screenshot live pages), ears (Sentry/Datadog/Rollbar errors + runtime checks), hands (verify fixes worked), and root-cause tools (source-map trace resolution, git regression blame), and debug tools (run tests, stream logs, query y
npm MIT