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.
-
uxcraftgithub.com/seance1723/uxcraftupdated this year
Opt-in UXCraft skill, CLI, and MCP server for AI coding agents — accessibility, design systems, UX research, and frontend handoff in one workflow.
npm MIT -
Agentic Research Orchestration for UX Research and Product Development. Vibe and handcoded by a social and data scientist with background in many research domains and open-source
MIT ★ 16 -
An MCP server that lets an AI assistant query a UX research repository with participant-level citations attached. It retrieves and counts; it does not interpret.
npm MIT -
MCP server for UX/UI Principles - 195 research-backed principles with citations, 12 UX smells, 12 flow checklists, and a pro mode (Principles Library API key) that adds full guides, AI prompts and interface audits. For Claude Code, Claude Desktop, Cursor,
npm MIT -
UX research synthesis. Upload interviews and get themes, findings, and verbatim quotes in minutes.
pypi -
userology-mcp-servergithub.com/Userology-Inc/userology-mcp-serverupdated this year
MCP server for the Userology UX research platform — connects Claude Code and Claude Desktop to Userology
MIT -
@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 -
Usability tests for websites, localhost and Figma flows: synthetic participants, real browser, evidence-backed reports. Works in Claude Code and Codex.
NOASSERTION -
synthetic-user-testing-mcpgithub.com/clauxel/synthetic-user-testing-mcpupdated this year
SyntheticUser Lab MCP: Paid remote MCP for synthetic user testing, UX validation, analytics, checkout, and readiness.
NOASSERTION -
flowdeck-mcpupdated this year
FlowDeck MCP sunucusu — Claude'un tarayıcıyla topladığı ekran görüntülerini FlowDeck arşivine yazar.
npm MIT -
Analyze product-demo videos with AI: extract screens, align them to narration, map UX flows, and compare experiences via a web app and MCP server.
pypi MIT ★ 2 -
@turbot-studio/mcp-servergithub.com/ruthkaufman/turbot-studio-mcpupdated this year
MCP server for Double Diamond design thinking methodology - helps engineers think through what to build
npm MIT -
bullet-mcpgithub.com/nikkoxgonzales/bullet-mcpupdated this year
MCP server for evidence-based bullet point validation. Scores lists against cognitive research (Miller's Law, serial position effects) with actionable feedback.
MIT ★ 1 -
Ask real people from your AI agent: human feedback, user testing, surveys and usability as one MCP tool call. Open standard (draft) + reference server. No key needed to try.
-
MCP server that turns a FigJam board into queryable LLM context — read via the Figma API, clustered with geometry + vision. No PDF export.
npm MIT ★ 1 -
@aetherya/mcpactive
Aetherya MCP server: test decisions on a synthetic audience from any MCP agent. Run research studies, site audits, copy tests, instant market reads and post or email simulations, then get a decision brief. Simulated, not real-user data.
npm MIT -
MCP server and CLI for UI research: search Refero, Mobbin, ScreensDesign and Dribbble, build a local screen library by category, capture web pages
MIT -
A native mobile design workflow for Claude Code and Codex. SwiftUI + Jetpack Compose, reference research, design reviews and purposeful motion. Noncommercial studies.
NOASSERTION ★ 1 -
Human factors research translated into design standards, code examples, and an MCP server for AI-assisted validation.
npm NOASSERTION ★ 5