uxloom MCP server
✓ VerifiedValidates UI/UX design completeness, state coverage, and WCAG accessibility compliance through agent-native state machine modeling.
Also known as uxloom-dev/uxloom
- Stars
- 4
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- 0.14.0
- Last commit
- Aug 9, 2026
- License
- MIT
What is uxloom MCP?
uxloom validates UI/UX design completeness, state coverage, and WCAG accessibility compliance through agent-native state machine modeling.
Summary generated from the project's README
About uxloom MCP server
UXLoom serves as a validation layer for UI/UX design, specifically targeting the gaps left by AI generators like v0 or Claude. It models user journeys as state machines to identify missing error states, unreachable screens, and dead ends. Developers use this tool to ensure design completeness and accessibility compliance before writing production code. It functions as an MCP server that integrates with clients like Claude Code and Codex, providing agent-native skills to automate the design review process.
The system evaluates designs against WCAG standards, checking for contrast failures, undersized touch targets, and localization issues like text overflow. Users can run local commands such as npx uxloom check for CI integration or npx uxloom audit to detect implementation drift in web or native environments. The tool uses a deterministic approach, producing byte-identical reports that allow design completeness to act as a gate in continuous integration pipelines.
What you can do with it
- 1Identify missing UI statesAsk an AI agent to find undiagnosed error, empty, or loading states within a generated user journey.
- 2Verify accessibility complianceUse the server to detect WCAG contrast failures and touch target size issues in a design.
- 3Automate design gates in CIConfigure your continuous integration pipeline to block merges if the design fails completeness checks.
Written from the project's README. Every use case is checked against a quote from it.
How to install uxloom MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall uxloom MCP in Claude Code
$ claude mcp add uxloom -- npx -y uxloomInstall uxloom MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"uxloom": {
"command": "npx",
"args": [
"-y",
"uxloom"
]
}
}
}Install uxloom MCP in VS Code
.vscode/mcp.json
{
"servers": {
"uxloom": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"uxloom"
]
}
}
}Install uxloom MCP in VS Code CLI
$ code --add-mcp '{"name":"uxloom","type":"stdio","command":"npx","args":["-y","uxloom"]}'Install uxloom MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"uxloom": {
"command": "npx",
"args": [
"-y",
"uxloom"
]
}
}
}Install uxloom MCP in Codex
$ codex mcp add uxloom -- npx -y uxloomInstall uxloom MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.uxloom] command = "npx" args = ["-y", "uxloom"]
Install uxloom MCP in Gemini CLI
$ gemini mcp add -s user uxloom npx -- -y uxloomInstall uxloom MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"uxloom": {
"command": "npx",
"args": [
"-y",
"uxloom"
]
}
}
}Configuration
UXLOOM_PROJECTPath to the project file (default: ./uxloom.project.json in the working directory)
Automated checks
Ran Nov 15, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachableuxloom-dev/uxloom is public and reachablegithub.com/uxloom-dev/uxloom ↗Pass
- Package names this repository as its sourceuxloom names uxloom-dev/uxloom as sourcenpmjs.com/package/uxloom ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for uxloomnpmjs.com/package/uxloom/v/0.14.0#provenance ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-08-09github.com/uxloom-dev/uxloom ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from uxloomPass
- No critical advisory in the package or its dependencies101 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubUXLoom
Your generator gave you 6 screens. UXLoom proves you're missing 9 states.
AI generators (v0, Lovable, Figma Make, Claude) produce happy-path screens. UXLoom is the critic layer: it models user journeys as state machines, treats screens as nodes with state contracts, and mechanically proves what's missing before a line of production code exists — unreachable screens, dead ends, missing error/empty/loading states, WCAG contrast failures, undersized touch targets, and labels that will overflow under localization.
Agent-native by design: the interface is an MCP server (works with Claude Code, Codex, and any MCP client), with Agent Skills included.
Deterministic by design: same input, byte-identical report — benchmarked
(packages/bench) at 1.000 precision/recall on a seeded
defect catalog, SHA-256-stable across processes, 1000 screens in under 5ms.
That's what lets design completeness gate CI, where an LLM opinion can't.
Website: uxloom.dev · npm: uxloom · MCP registry: io.github.uxloom-dev/uxloom ·

Packages
| Package | What it is |
|---|---|
@uxloom/journeygraph |
The open design-as-data format: journeys as state machines, screens as nodes with required states |
@uxloom/critics |
The validators: journey completeness, state coverage, WCAG contrast, touch targets, text expansion |
uxloom |
The MCP server + Agent Skills — the interface agents use |
New here? Start with the Quickstart — prerequisites, the Claude Code walkthrough, what to say to your agent, and troubleshooting.

Quick start (agents)
# Claude Code
claude mcp add uxloom -- npx -y uxloom
# Codex CLI
codex mcp add uxloom -- npx -y uxloom
The project file (uxloom.project.json) lives in your workspace and belongs
in git — the design is data, versioned next to the code it specifies.
Quick start (humans & CI)
npx uxloom init # one-command setup: MCP config + agent skill + starter file
npx uxloom preview # live mocks (themed, commentable, EDITABLE in the browser)
npx uxloom export # shareable HTML — plus --svg (Figma/Penpot import; add
# --manifest for the round-trip key) and --png (playwright)
npx uxloom check # design completeness — exit 1 on errors, CI-ready
npx uxloom audit # implementation drift — web AND native (Swift/Kotlin/
# Dart/Java markers); --live verifies the real DOM;
# --design <file|dir> audits a Figma/Penpot export vs the contract
npx uxloom diff # human-readable design diffs for PR review
Evidence-based design: every decision in the contract can carry its
rationale — reasoning, rejected alternatives with pros/cons, sources,
confidence — enforced by the critics once adopted, iterated through a
bounded design_review loop (max 3 rounds), and shown to stakeholders in
the preview's evidence panel (ⓘ) and exports. The design doesn't just
validate; it argues its case.
Agent-addressable comments: a reviewer drops a pinned comment in the
preview and clicks "→ agent". The comment becomes a work item any Gen-AI
model can read with full context — comment_context returns the pinned
layout block, the screen contract, the journey references, and the current
findings for that screen — act on, and resolve back into the preview with
a note. One click from feedback to addressed.

CI-native: check and audit take --json, --sarif (GitHub code
scanning), and --github (inline PR annotations). Brownfield-ready:
--update-baseline freezes existing findings so only new drift blocks;
uxloom.config.json tunes thresholds to your accessibility bar. Full
documentation: uxloom.dev/docs.html.

Add it to CI and a happy-path-only design can never merge:
- run: npx uxloom check design/uxloom.project.json
Workflow (also shipped as a skill in packages/mcp-server/skills/):
project_init → brief_start/brief_answer → journey_define →
screen_register → project_validate → fix → repeat until zero errors →
coverage_report.
Does it actually catch things?
tools/dogfood.mjs drives the real MCP server through three products, twice
each: screens as a happy-path generator hands them over, then repaired using
the validation report. Artifacts in examples/.
| Product | Generated (happy-path) | Repaired |
|---|---|---|
shopmweb — e-commerce checkout (mWeb + Android) |
9 errors, 6 warnings | 0 / 0 |
taskflow — SaaS signup/onboarding (web) |
1 error, 6 warnings | 0 / 0 |
ridenow — ride booking (iOS + Android, offline-heavy) |
3 errors, 7 warnings | 0 / 0 |
Caught: an unreachable promo screen, dead-end verification states, five
undesigned payment/error states, a 2.4:1 contrast button, a 40px touch target
on Android, a checkout label that breaks in German, and three products' worth
of missing offline states. Zero errors and zero warnings is reachable
honestly — screens declare documented exemptions where a baseline state
genuinely cannot apply, and contradictory exemptions are flagged.
Development
npm install
npm run typecheck
npm test
Status
Released and maintained: on npm and
the official MCP registry, with the benchmark scorecard published in every
GitHub release. The
JourneyGraph format (formatVersion: "0.1") may evolve until 1.0; releases
follow RELEASING.md — every surface is drift-checked in CI.
License
MIT
uxloom MCP questions
How do I add uxloom MCP to Claude Code?
Run claude mcp add uxloom -- npx -y uxloom in your terminal. Add --scope user to make it available in every project.
How do I add uxloom MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How can I use UXLoom with AI agents?
You can add it to Claude Code or Codex CLI using npx to enable Agent Skills for design validation.
Can it audit existing designs from Figma or Penpot?
Yes, the audit command can compare a Figma or Penpot export against your design contract.