tpu-vllm-v5e1-embed2

Level CLocal

MCP devops agent for serving EmbeddingGemma 2 with vLLM on a Cloud TPU v5e-1 Flex-start Queued Resource

⭐ 3 · Parent repoDevOps & DeploymentPythonRepo ↗Updated 2026-11-11

Installation

MCP client config (paste into mcp.json)

{
  "mcpServers": {
    "xbill9-gemma4-dev-tpu-vllm-v5e1-embed2": {
      "command": "uvx",
      "args": [
        "tpu-vllm-v5e1-embed2"
      ]
    }
  }
}

Agent install prompt

Copy and paste into Cursor / Claude / other agents to install this MCP for you

Please read this MCP repository and install it into my current environment:
https://github.com/xbill9/gemma4-dev/tree/main/tpu-vllm-v5e1-embed2

Known working client config (can write into mcp.json):
{
  "mcpServers": {
    "xbill9-gemma4-dev-tpu-vllm-v5e1-embed2": {
      "command": "uvx",
      "args": [
        "tpu-vllm-v5e1-embed2"
      ]
    }
  }
}

Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.

Related servers