1. Conduid
  2. Social
  3. io.github.jaimenbell/vllm-ops-mcp
MCP server · Social

io.github.jaimenbell/vllm-ops-mcp

· github.com/jaimenbell/vllm-ops-mcp

Read-only ops/health MCP server for a local vLLM instance: health tiers, GPU/VRAM, service status.

Unclaimed social
InstallView source
37Low

Scored 2 months ago · breakdown

About io.github.jaimenbell/vllm-ops-mcp

io.github.jaimenbell/vllm-ops-mcp is an MCP server in the Social category: read-only ops/health MCP server for a local vLLM instance: health tiers, GPU/VRAM, service status.

Install

uvx
uvx vllm-ops-mcp
pip
pip install vllm-ops-mcp

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Tools (6)

check_health(deep: bool = False)`deep=False`: GET `/v1/models` liveness check (same signal as `llm_router.LocalLLM.is_healthy()`). `deep=True`: additionally fires one minimal real `/v1/chat/completions` call (mirrors `check-vllm.cmd`'s two-stage probe) to confirm the server actually *generates*, not just *reports a model loaded*.

Parameters not published.

get_gpu_status`nvidia-smi` wrapper: per-GPU VRAM used/total + utilization%, plus per-process VRAM via `--query-compute-apps`.

Parameters not published.

get_serve_configRead-only launch-flag introspection. **Prefers the LIVE process's actual argv** (`/proc/<pid>/cmdline` of the systemd unit's `MainPID` -- ground truth of what's running right now), falling back to the static exec script (local mirror via `VLLM_OPS_MCP_SERVE_CONFIG_PATH`, else a live `cat` of the WSL-side exec script) only when the process isn't up.

Parameters not published.

get_service_status`systemctl show <unit> -p ...` (structured property output, not free-text parsing) via `wsl -d <distro>` from the Windows host, or native `systemctl` if this server itself runs inside WSL2/Linux. Returns load/active/sub state, restart count, main PID, last-active timestamp.

Parameters not published.

list_models`/v1/models` passthrough.

Parameters not published.

test_completion(prompt, max_tokens=16)On-demand real completion with a caller-supplied prompt, for manual sanity checks.

Parameters not published.

Ask AI

✦

Ask AI about io.github.jaimenbell/vllm-ops-mcp

Powered by Claude · Grounded in docs

I know everything about io.github.jaimenbell/vllm-ops-mcp. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

6 checks have not been run yet.

Questions

About io.github.jaimenbell/vllm-ops-mcp

How do I install io.github.jaimenbell/vllm-ops-mcp?

Run uvx vllm-ops-mcp, then add the server to your MCP client's configuration.

Is io.github.jaimenbell/vllm-ops-mcp safe to use with an AI agent?

Its trust score is 37 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is io.github.jaimenbell/vllm-ops-mcp still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.