Skip to content
mcp/harbor
Grok

llmxray for Grok

io.github.lognebudo/llmxray

What went wrong with your own Ollama calls, in sentences with the fix. Local, read-only.

client:Grok transport:stdio runtime:npm

Install llmxray in Grok

.mcp.json (in your project root)

Held in this page only — never stored, logged, or sent anywhere but back to your screen. 

{
  "mcpServers": {
    "llmxray": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "llmxray"
      ],
      "env": {
        "LLMXRAY_URL": "<LLMXRAY_URL>",
        "OLLAMA_URL": "<OLLAMA_URL>"
      }
    }
  }
}

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

llmxray in other clients

llmxray MCP server