UIZZE
Stop generic UI slop in Codex, Claude Code, and Cursor.
What it can do
- Create Ui Design Contract: Create the required machine-readable design contract from the target repository, product intent, states, constraints, and UIZZE evidence before implementation.
- Get Ui Reference Brief: Search UIZZE for deeper product evidence, screenshots, flows, states, components, and implementation guidance before creating or refining a design contract.
- Validate Implementation Manifest: Validate changed files, components, states, control outcomes, design-system reuse, and screenshot evidence against a UIZZE design contract.
What data it sees
Do you need an account
An API key from the service settings is required
Stop generic UI slop in Codex, Claude Code, and Cursor. Search 800,000+ real web and iOS screens, build design contracts and reference packs, audit implementations, and critique rendered screenshots without leaving your coding agent.
How to connect
How to connect UIZZE to Claude
The server address to paste into Claude settings:
https://uizze--smlbushi.run.tools
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect UIZZE to ChatGPT
The server address to paste into ChatGPT settings:
https://uizze--smlbushi.run.tools
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect UIZZE to Cursor
The server address to paste into Cursor settings:
https://uizze--smlbushi.run.tools
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (14)
Raw names from tools/list. Only developers need these.
| create_ui_design_contract | Create the required machine-readable design contract from the target repository, product intent, states, constraints, and UIZZE evidence before implementation. |
| get_ui_reference_brief | Search UIZZE for deeper product evidence, screenshots, flows, states, components, and implementation guidance before creating or refining a design contract. |
| validate_implementation_manifest | Validate changed files, components, states, control outcomes, design-system reuse, and screenshot evidence against a UIZZE design contract. |
| search_design_patterns | Search structured UIZZE design analyses for surfaces, components, states, anti-patterns, and platform conventions. |
| get_screen_design_analysis | Fetch ontology-backed design evidence for one UIZZE screen. |
| critique_implemented_ui | Critique a rendered UI screenshot against its design contract, implementation manifest, reference evidence, and deterministic anti-slop checks. |
| audit_implemented_ui | Run deterministic anti-slop checks on a screenshot and optional HTML or CSS artifacts without persisting the screenshot. |
| search_ui_references | Search 800,000+ real web and iOS screens for specific product, workflow, state, or UI references. |
| compare_ui_references | Compare how two to four named products handle the same screen or flow using grouped real references and source links. |
| search_ui_elements | Search real controls and workflow elements such as forms, tables, dialogs, settings rows, empty states, and onboarding steps. |
| get_screen_reference | Fetch one screen as an agent-ready reference pack with its screenshot, metadata, OCR excerpt, guidance, and source links. |
| get_app_reference_pack | Fetch app-level context with selected flows, screens, navigation patterns, density, and repeated product structure. |
| get_flow_reference_pack | Fetch an ordered multi-screen flow with implementation guidance and anti-generic checks. |
| get_collection_reference_pack | Fetch a user-curated collection as a paginated UI reference pack. |