Splendorize

Splendorize MCP Server

Connect Splendorize to Claude, Codex, Cursor or any MCP client. Your assistant sees what works on your landing pages, builds the evidence, drafts improvements and experiments, and checks previews before you ship. Every write needs an explicit OAuth scope.

• Endpoint: https://mcp.splendorize.com/mcp (Streamable HTTP)
• Auth: OAuth, sign in with your Splendorize account
• Website: https://splendorize.com/mcp
• Official MCP Registry: com.splendorize/mcp

What you can do

• Read site intelligence: page-type opportunities, next moves, signal status, landing performance and SEO.
• Build evidence packs and generate improvement suggestions.
• Draft experiments from suggestions and move them through review.
• Scan a preview URL and validate instrumentation before you ship.
• Set up and configure sites, and manage recommendations, experiments, implementation runs and integrations (GitHub, search, revenue).

Customer-facing changes ask for your confirmation in the client. A paid Splendorize plan is required.

Connect

The server uses OAuth. Your client opens a browser window, you sign in with your Splendorize account and approve access. You do not copy an API key.

Claude (claude.ai and Claude Desktop)

Open Settings → Connectors → Add custom connector, enter https://mcp.splendorize.com/mcp and select Connect.

Claude Code

claude mcp add --transport http splendorize https://mcp.splendorize.com/mcp

Then run /mcp in Claude Code and authenticate splendorize.

Codex CLI

codex mcp add splendorize --url https://mcp.splendorize.com/mcp

codex mcp login splendorize

Cursor

Add this to ~/.cursor/mcp.json:

{

"mcpServers": { "splendorize": { "url": "https://mcp.splendorize.com/mcp" } } }

VS Code

code --add-mcp '{"name":"splendorize","type":"http","url":"https://mcp.splendorize.com/mcp"}'

Gemini CLI

gemini mcp add --transport http splendorize https://mcp.splendorize.com/mcp

ChatGPT and other clients

Add a custom connector (in ChatGPT, developer mode) with the URL https://mcp.splendorize.com/mcp. Any client that supports Streamable HTTP and MCP OAuth works.

Tools

Your client always gets the current list and schemas from tools/list.

• Intelligence: rank_page_type_opportunities, build_evidence_pack, generate_suggestion
• Drafts and experiments: draft_experiment_from_suggestion, transition_suggestion, manage_experiment, manage_recommendation
• Preview and checks: scan_preview_url, validate_instrumentation, verify_site_install
• Sites and integrations: create_site, configure_site, manage_implementation, manage_github_integration, manage_search_integration, manage_revenue_settings

Prompts: draft_landing_page_improvement_brief, implement_this_change_safely, site_strategy_brief, review_preview_against_evidence. Resources expose sites, dashboards, landing performance, SEO, next moves, recommended changes, evidence, suggestions, experiments and journeys.

Authentication and account

OAuth 2.1 with PKCE and dynamic client registration. You choose the sites and scopes on the consent screen. Scopes: read:intelligence, read:revenue_aggregate, write:drafts, write:sites, write:recommendations, write:experiments, write:implementation, write:integrations.

You need a Splendorize account on a paid plan.

Links

• Website: https://splendorize.com
• MCP setup page: https://splendorize.com/mcp
• Privacy policy: https://splendorize.com/privacy

About this repository

This repository is the public home of the hosted Splendorize MCP server. It holds this setup guide and the registry metadata (server.json for the official MCP Registry, glama.json for Glama). The server runs as a hosted service at https://mcp.splendorize.com/mcp. Its source code is not in this repository.

Found a problem or have a question? Open an issue.

License

The contents of this repository are available under the MIT License.