General Tools
xpay.sh
Provides access to an ecommerce ChatGPT prompt library, allowing users to list, search, and retrieve prompts.
ENDPOINT 1
https://prompts-mcp.xpay.sh/mcp
MCP server metadata
- Name
- Ecommerce Prompts
- Version
- 1.0.0
Known tools 4
list_collectionsList every prompt collection in the free ecommerce ChatGPT prompt library at xpay.
Inferred read-onlysearch_promptsSearch the whole ecommerce prompt library by keyword (matches prompt title, summary, body, and collection).
Inferred read-onlyget_promptGet one prompt by its id, with the full template body, variables, recommended model, pro tip, and source URL.
Inferred read-onlyCONNECT 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.ecommerce-prompts]
url = "https://prompts-mcp.xpay.sh/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"ecommerce-prompts": {
"type": "http",
"url": "https://prompts-mcp.xpay.sh/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: ecommerce-prompts
Remote MCP URL: https://prompts-mcp.xpay.sh/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": {
"ecommerce-prompts": {
"url": "https://prompts-mcp.xpay.sh/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"ecommerce-prompts": {
"type": "http",
"url": "https://prompts-mcp.xpay.sh/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "ecommerce-prompts",
"transport": "streamable-http",
"url": "https://prompts-mcp.xpay.sh/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for xpay.sh was fetched 2026-08-03T12:31:32.693Z.
xpay.sh is assessed as Trusted: Domain runs a meaningful technology spend, consistent with a real business.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.