# Splendorize

An MCP server that connects Splendorize to Claude, Codex, Cursor and other IDEs. Your agent sees what works on your landing page, suggests improvements, and helps you draft and run experiments.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: splendorize
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/splendorize/splendorize-mcp
- Updated: 2026-10-29
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/splendorize

## What it does

Splendorize gives your agent access to landing-page analytics: page-type opportunities, signal status, performance metrics and SEO data. The agent can build evidence packs, generate improvement suggestions, draft experiments and move them through review stages.

Authentication uses OAuth. When you connect, your client opens a browser, you sign in with your Splendorize account and choose which sites and permissions to grant. Available tools cover intelligence gathering, evidence building, suggestion generation, experiment drafting and management. Any customer-facing change requires your confirmation in the client.

You need a paid Splendorize plan. The server runs at `https://mcp.splendorize.com/mcp` and supports granular OAuth scopes: `read:intelligence`, `read:revenue_aggregate`, `write:drafts`, `write:sites`, `write:recommendations`, `write:experiments`, `write:implementation`, `write:integrations`.

## Requirements
- Remote server: `https://mcp.splendorize.com/mcp`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http mcp https://mcp.splendorize.com/mcp
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add splendorize --url https://mcp.splendorize.com/mcp
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "splendorize": {
            "url": "https://mcp.splendorize.com/mcp"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "splendorize": {
            "type": "http",
            "url": "https://mcp.splendorize.com/mcp"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http splendorize https://mcp.splendorize.com/mcp
```

## When to use it
- find improvement opportunities on a landing page by section type
- gather evidence and build a recommendation for a specific change
- draft and validate an experiment before running it live
- scan a preview URL and verify tracking instrumentation

## Example prompts
- Show me what we can improve on our landing page and help build the evidence for one opportunity.
- Check this preview URL and make sure the tracking is set up correctly.
- Draft an experiment from this suggestion and move it to Ready for review.

## Similar
- [paid-landing-page-audit](https://affpapa.org/en/nevibecode/skills/paid-landing-page-audit.md) — skill · 26700 installs
- [creating-experiments](https://affpapa.org/en/nevibecode/skills/creating-experiments.md) — skill · 431 installs
- [synthesize-learnings](https://affpapa.org/en/nevibecode/commands/synthesize-learnings.md) — command · ★ 450 repo stars
- [optimize-nurture](https://affpapa.org/en/nevibecode/commands/optimize-nurture.md) — command · ★ 450 repo stars
- [Hovercode](https://affpapa.org/en/nevibecode/mcp/hovercode.md) — MCP server
- [landing-page-review](https://affpapa.org/en/nevibecode/skills/landing-page-review.md) — skill · ★ 116 repo stars

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
