Check if a task runs locally vs cloud. Save money on calls that don't need cloud inference.
Paste into claude_desktop_config.json:
{
"mcpServers": {
"local-model-suitability-mcp": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://local-model-suitability-mcp-production.up.railway.app"
]
}
}
}Run in a terminal:
claude mcp add --transport http local-model-suitability-mcp https://local-model-suitability-mcp-production.up.railway.app
Paste into .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):
{
"mcpServers": {
"local-model-suitability-mcp": {
"url": "https://local-model-suitability-mcp-production.up.railway.app"
}
}
}Transport: http - Hosted remote (streamable HTTP). Nothing runs on your machine - the config above connects your client straight to the vendor's endpoint (older clients bridge via npx mcp-remote).
Auth: the remote endpoint may prompt for OAuth or an API key on first connect - see the vendor's docs.
https://wingmanprotocol.com/mcp.