LocalFree

Vllm Ops MCP server

jaimenbell/vllm-ops-mcp

Read-only health checks for a local vLLM instance: liveness and real-completion tiers, GPU and VRAM status, service status and serve-flag introspection.

0 GitHub stars

Install Vllm Ops in Claude Code

Claude Code
claude mcp add vllm-ops -- uvx vllm-ops-mcp
mcp.json (Claude Desktop, Cursor, VS Code, Windsurf)
{
  "mcpServers": {
    "vllm-ops": {
      "command": "uvx",
      "args": [
        "vllm-ops-mcp"
      ]
    }
  }
}

Frequently asked questions

What does the Vllm Ops MCP server do?

Read-only health checks for a local vLLM instance: liveness and real-completion tiers, GPU and VRAM status, service status and serve-flag introspection.

Is the Vllm Ops MCP server free?

Yes, most likely. Open source and no paid account or API key is mentioned in the listing. Check the provider for current pricing.

Does Vllm Ops run locally or remotely?

Local. Runs on your machine (stdio). You install it with npx, uvx, Docker or from source.

How do I add Vllm Ops to Claude Code?

Run: claude mcp add vllm-ops -- uvx vllm-ops-mcp

More monitoring & observability MCP servers

View all