Content Tools
curatorapproved.com
Searches, retrieves, and renders published Curator selections as interactive cards in chat.
ENDPOINT 1
https://curatorapproved.com/api/mcp
MCP server metadata
- Name
- the-curator-mcp-server
- Version
- 0.1.0
Search The Curator public catalog, inspect facts, then call render_curator_items with chosen IDs to show cards. Prices are dated observations, not live offers. Preserve configuration notes, referral disclosures and unknowns. This server cannot purchase, publish, edit the catalog, access private research, or persist wishlists.
Known tools 3
get_curator_itemRetrieve one published Curator item by a stable ID returned from search_curator.
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.the-curator-mcp-server]
url = "https://curatorapproved.com/api/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"the-curator-mcp-server": {
"type": "http",
"url": "https://curatorapproved.com/api/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: the-curator-mcp-server
Remote MCP URL: https://curatorapproved.com/api/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": {
"the-curator-mcp-server": {
"url": "https://curatorapproved.com/api/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"the-curator-mcp-server": {
"type": "http",
"url": "https://curatorapproved.com/api/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "the-curator-mcp-server",
"transport": "streamable-http",
"url": "https://curatorapproved.com/api/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.