Vllm Ops MCP

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/jaimenbell-vllm-ops-mcp

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

5 read · 0 write · 0 delete · 1 not yet classified

Secrets

None asked for

Install scripts

Not scanned yet

Runs as

Python package

Tools (6)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• check_health

  Two-stage health probe for the local vLLM server, mirroring check-vllm.cmd. deep=False (default): GET /v1/models liveness check only. deep=True: additionally fires one minimal real /v1/chat/completions call to confirm the server actually generates text, not just reports a model loaded (rate-limited -- this consumes real GPU inference cycles on shared infra). Returns {ok, status: up|degraded|down, tier, model_id, latency_ms, completion_s, error}.

• get_gpu_status

  nvidia-smi wrapper: per-GPU VRAM used/total and utilization%, plus per-process VRAM usage (to catch VRAM-overshoot). Read-only.

• get_serve_config

  Read-only introspection of the current vLLM launch flags. Prefers the LIVE process's real argv (/proc/<pid>/cmdline of the systemd unit's MainPID) as ground truth; falls back to the static exec script if the process isn't currently up. vLLM does not expose its own launch flags over the API, so this never queries the server itself. Any argv value following a flag matching a known-sensitive pattern (token/key/secret/password/credential) is redacted before being returned.

• get_service_status

  systemd unit status for the vLLM service (via `wsl -d <distro> -- systemctl show`, or native systemctl if this server runs inside WSL2/Linux). Returns load/active/sub state, restart count, main PID, and last-active timestamp. Read-only -- never starts/stops the unit.

• list_models

  GET /v1/models passthrough -- lists model IDs currently loaded/served.

• test_completion

  On-demand real /v1/chat/completions call with a caller-supplied prompt, for manual sanity-checking (same mechanism as check_health(deep=True) but user-controlled). Rate-limited -- consumes real GPU inference cycles on shared infra. max_tokens is clamped server-side to config.MAX_TEST_COMPLETION_TOKENS and the prompt is capped at config.MAX_TEST_COMPLETION_PROMPT_CHARS (oversized prompts are rejected) -- the rate limiter bounds call frequency, not the cost of a single call. Returns {ok, model_id, completion_s, text, error}.

Signals

Stars

0

Forks

0

Open issues

0

Weekly downloads

51

Last commit

Aug 12, 2026 (2 months ago)

Last release

Jul 24, 2026 (3 months ago)

Last package publish

Jul 24, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.jaimenbell/vllm-ops-mcp

Version

0.1.0

Auth

No auth

Packages

pypi vllm-ops-mcp

License

MIT

Repository

github.com/jaimenbell/vllm-ops-mcp

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql