Skip to content
mcp/harbor
VS Code

llmxray for VS Code

io.github.lognebudo/llmxray

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

client:VS Code transport:stdio runtime:npm

Install llmxray in VS Code

.vscode/mcp.json 

{
  "inputs": [
    {
      "type": "promptString",
      "id": "llmxray-url",
      "description": "LLMXRAY_URL",
      "password": true
    },
    {
      "type": "promptString",
      "id": "ollama-url",
      "description": "OLLAMA_URL",
      "password": true
    }
  ],
  "servers": {
    "llmxray": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "llmxray"
      ],
      "env": {
        "LLMXRAY_URL": "${input:llmxray-url}",
        "OLLAMA_URL": "${input:ollama-url}"
      }
    }
  }
}

VS Code prompts for each input the first time the server starts, so no secret is written to the file. VS Code docs

llmxray in other clients

llmxray MCP server