Vllm Ops MCP Server
by jaimenbellio.github.jaimenbell/vllm-ops-mcpv0.1.0
Read-only health checks for a local vLLM instance: liveness and real-completion tiers, GPU and VRAM status, service status and serve-flag introspection.
context tax
queued
security
queued
cold start
queued
freshness
Maintained59d ago
Install Vllm Ops MCP server
Install in Claude Code
claude mcp add vllm-ops -- uvx vllm-ops-mcpInstall in Cursor
{
"mcpServers": {
"vllm-ops": {
"command": "uvx",
"args": [
"vllm-ops-mcp"
]
}
}
}Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project).
Install in Claude Desktop
{
"mcpServers": {
"vllm-ops": {
"command": "uvx",
"args": [
"vllm-ops-mcp"
]
}
}
}Settings → Developer → Edit Config (claude_desktop_config.json), then restart.
Install in VS Code
{
"servers": {
"vllm-ops": {
"type": "stdio",
"command": "uvx",
"args": [
"vllm-ops-mcp"
]
}
}
}Add to .vscode/mcp.json in your workspace.
Install in Windsurf
{
"mcpServers": {
"vllm-ops": {
"command": "uvx",
"args": [
"vllm-ops-mcp"
]
}
}
}Add to ~/.codeium/windsurf/mcp_config.json.
Freshness
Maintained — last maintenance signal 59d ago. The newest of the signals below sets the band.
Last commit (default branch)
2026-08-12 · 59d ago · GitHub
Latest release
no data · GitHub
Package published
no data · npm/PyPI
Registry entry updated
2026-07-24 · 3mo ago · official registry · v0.1.0
FAQ
›How do I install the Vllm Ops MCP server in Claude Code?
Run: claude mcp add vllm-ops -- uvx vllm-ops-mcp. For Cursor, VS Code, Claude Desktop and Windsurf, use the install tabs above.
›Does Vllm Ops require an API key?
No required environment variables are declared in its published metadata.
›Can I use Vllm Ops as a remote (hosted) MCP server?
No hosted endpoint is published; it runs locally over stdio.
›Is Vllm Ops in the official MCP registry?
Yes, as io.github.jaimenbell/vllm-ops-mcp.
Alternatives to Vllm Ops
Other monitoring & observability MCP servers.
NetdataActiveDiscovery, exploration, reporting and root cause analysis over Netdata metrics, logs, systems, containers, processes and network connections.
FirecrawlActiveFirecrawl web scraping: search, scrape, crawl, map and extract structured data, with live browser interaction and website change monitoring.
WigoloActiveLocal web search, fetching, crawling, extraction and research, with multi-engine search, local ML reranking, a SQLite cache and JavaScript rendering.
ZoteroActiveSearch, read, annotate, and add to your Zotero research library, local or web.
ExaActiveConnect AI agents to Exa for web search, content fetching, and multi-step research.
KubefwdActiveKubernetes bulk port forwarding with service discovery, /etc/hosts management, traffic monitoring and pod log streaming.