Skip to content
mcp/harbor
Grok

LMX Cloud LLM Inference for Grok

io.lmxcloud/mcp-server

OpenAI-compatible LLM MCP (7 tools); chat via balance key or x402 USDC on Base

client:Grok transport:streamable-http tools:9

Install LMX Cloud LLM Inference in Grok

.mcp.json (in your project root) 

{
  "mcpServers": {
    "mcp-server": {
      "type": "http",
      "url": "https://mcp.lmxcloud.io/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

What Grok can do once it is connected

LMX Cloud LLM Inference in other clients

LMX Cloud LLM Inference MCP server