Splendorize
com.splendorizePublished by splendorize.comOfficial publisherv0.8.0Updated Oct 29, 2026
AI agents that find landing-page improvements, draft experiments and measure the results.
Overview
Hosted Splendorize MCP server that lets an assistant analyze landing pages, draft improvement experiments and check previews before shipping.
- 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 shipping
- Set up and configure sites, and manage recommendations, experiments, implementation runs and integrations (GitHub, search, revenue)
- When to use it
- Useful when you run landing pages on Splendorize and want an assistant to turn performance evidence into concrete improvement suggestions, experiment drafts and pre-ship preview checks without switching tools.
- Requirements
- Remote Streamable HTTP endpoint at mcp.splendorize.com/mcp; OAuth sign-in with a Splendorize account on a paid plan; client must support Streamable HTTP and MCP OAuth (OAuth 2.1 with PKCE and dynamic client registration). No API key to copy.
Installation
In SourceWeft
- Open Splendorize in the dashboard and add it to a workspace.
- Connect the required credentials. They are stored privately and never shown on public pages.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/com.splendorize%2Fmcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.
{
"mcpServers": {
"splendorize": {
"type": "http",
"url": "https://mcp.splendorize.com/mcp"
}
}
}README
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
Then run /mcp in Claude Code and authenticate splendorize.
Codex CLI
Cursor
Add this to ~/.cursor/mcp.json:
VS Code
Gemini CLI
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.
Source: README.md at commit b2feb30
Tools
0Version history
1- v0.8.0LatestOct 29, 2026
Score
85% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts