Developer Tools

uxgen.ai

Provides tools for generating design themes, images, page renders, and audits to assist in building websites.

1 endpoint9 known toolsFirst detected August 25, 2026Last detected August 25, 2026

ENDPOINT 1

https://www.uxgen.ai/mcp

No auth detected

MCP server metadata

Name: uxgen
Version: 0.1.0

Capabilities

tools

Server instructions

uxgen teaches your agent the trade of selling: the order of the sections, the photography, a locked grammar, and an audit that rejects a page unable to take money. Account: not signed in (subscription expire). 🔴 STATUS ON 24/08/2026: only `uxgen_image` executes — it is the only call that costs real money, so the only one a quota makes sense behind. The other eight tools return an explicit refusal: do not invent their result, and do not build a page assuming they answered. 💰 IMAGE ALLOWANCE — every account gets an amount per month, and every image really consumes it. A quota refusal carries a JSON block with `code` and `reessayable`: when `reessayable` is false, IT IS A DECISION, NOT AN OUTAGE — stop, do not loop, and tell your user.

Known tools 9

uxgen_brief

CALL THIS FIRST for any page or site you are about to build, before writing a single line.

Inferred read-only

uxgen_theme

Turns a brand color and an adjective into a COMPLETE set of CSS variables: palette (3 roles + 2 derived), font pair, radii, shadows, rhythm, motion.

Inferred read-only

uxgen_image

THE MATERIAL OF THE PAGE — scene OR packshot.

Inferred read-only

uxgen_render

MAKES THE PAGE VISIBLE.

Inferred read-only

uxgen_audit

MEASURES the page and RETURNS NAMED GAPS.

Inferred read-only

uxgen_ameliorer

🎯 THE ONLY EXTERNAL JUDGE IN THE PRODUCT, ~30 SECONDS BY DEFAULT.

Inferred read-only

uxgen_status

🚨 DO NOT CALL THIS TO GET YOUR BEARINGS: the path is returned by uxgen_brief, and this response is LONG (~5,500 tokens; "complet" makes it ~14,700).

Inferred read-only

uxgen_packshot

COMPOSES THE CLIENT'S PRODUCT ONTO A REAL PHOTOGRAPH.

Inferred read-only

uxgen_publier

CALL THIS BEFORE ANNOUNCING THAT IT IS DONE, on the page you have just written.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.uxgen]
url = "https://www.uxgen.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "uxgen": {
      "type": "http",
      "url": "https://www.uxgen.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: uxgen
Remote MCP URL: https://www.uxgen.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "uxgen": {
      "url": "https://www.uxgen.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "uxgen": {
      "type": "http",
      "url": "https://www.uxgen.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "uxgen",
  "transport": "streamable-http",
  "url": "https://www.uxgen.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.