Xpensiv MCP Server
OfficialThis server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
xpensiv-mcp
Your AI wrote the app. Xpensiv makes it sexy.
Xpensiv is the Vertical Foundation Model (VFM) for Design, the Anti AI-Slop Model. It is API and MCP first, so a developer's AI agent calls it on an app it built and asks, design first, what to change.
This package is the Xpensiv MCP server. It runs locally over stdio and calls the Xpensiv REST API at https://xpensiv.si.
Install
Node 18 or newer.
npx -y xpensiv-mcpSet XPENSIV_API_KEY to a key from https://xpensiv.si/console/keys. The key is shown once and starts with xpk_. Do not commit it. XPENSIV_API_URL overrides the host.
Example client config:
{
"mcpServers": {
"xpensiv": {
"command": "npx",
"args": ["-y", "xpensiv-mcp"],
"env": { "XPENSIV_API_KEY": "xpk_..." }
}
}
}Related MCP server: ui-optimizer-mcp
Tools
check_app: start a design check on a public URL. Returns a check ID.get_check: read the status and the fix list for a check ID. A check takes 1 to 3 minutes.list_checks: list your recent checks.
Hosted server
The hosted Streamable HTTP server is POST https://xpensiv.si/mcp with Authorization: Bearer xpk_....
How a check works
The hosted service sends screenshots of the page to a vision model and returns findings next to browser measurements. If the model is unavailable, the result says it fell back to automated findings only. A check covers one page, without clicks, forms or signed-in flows. Read the findings before you change anything.
Develop
npm testLicence
MIT. Copyright Xpensiv SI. Website: https://xpensiv.si
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
The website checker for AI agents. One call: verdict, score out of 100, fix list.
Website checker for AI coding agents. Measures your site in a real browser, with evidence.
Synthetic UX reviews, findings, evidence images, and repair prompts. OAuth required.
Scan a website for AI search and agent readiness, then get a fix checklist for your agent.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables AI agents to score live URLs against a deterministic design contract, validate DTCG tokens and Lottie animations, audit accessibility, and retrieve design-system contracts, catalogs, and review rubrics.175 npmMIT
- AlicenseAqualityCmaintenanceEnables AI-driven UI inspection and optimization by scanning websites with configurable viewports, capturing screenshots, running deterministic accessibility and layout checks, and generating prioritized reports with fix prompts.2MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to analyze public websites, follow progress, retrieve shareable reports, compare multiple URLs, list checks and recent activity, and surface fixes ranked by impact.Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables MCP clients to launch AI persona tests against public web app URLs in a real browser, then retrieve status, findings, screenshots, and combined fix prompts for coding agents.MIT