WhichModel for Grok
io.github.which-model/whichmodel
Cost-optimized LLM model routing recommendations for autonomous AI agents
client:Grok
transport:streamable-http
Install WhichModel in Grok
.mcp.json (in your project root)
{
"mcpServers": {
"whichmodel": {
"type": "http",
"url": "https://whichmodel.dev/mcp"
}
}
}Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs