vram-mcp

An MCP server that lets AI agents inspect and free NVIDIA GPU VRAM by managing Ollama models. Handy when you juggle several local models across projects on a single GPU and an agent needs to make room before loading the next one.

• NVIDIA + Ollama only for v1.

• Degrades gracefully when nvidia-smi is absent: VRAM readings become unknown, but model list / unload / warm still work.

Tools

Related MCP server: Ollama MCP Server

Requirements

• Ollama running locally (or reachable via OLLAMA_BASE_URL).

• NVIDIA GPU + drivers for VRAM numbers. nvidia-smi is optional — without it, VRAM is reported as unknown and model operations still function.

• Python 3.10+.

Install

Run directly with uv (no install needed):

uvx vram-mcp

Or install from source for development:

git clone https://github.com/sushiHex/vram-mcp
cd vram-mcp
pip install -e .

Run

vram-mcp

The server speaks MCP over stdio, so it is normally launched by an MCP client rather than by hand.

MCP client config

Add this to your MCP client's mcpServers config (e.g. Claude Code / Claude Desktop):

{
  "mcpServers": {
    "vram": {
      "command": "uvx",
      "args": ["vram-mcp"]
    }
  }
}

Configuration

• OLLAMA_BASE_URL — Ollama endpoint. Defaults to http://127.0.0.1:11434.

Multi-session coordination

Since every session runs its own vram-mcp process, coordination happens via:

• Claims — a shared, file-based ledger (~/.cache/vram-mcp/claims.json) recording who's using a model and why. Call claim() when you start relying on a model; renew() periodically if still in use. An un-renewed claim simply expires — no cleanup needed if your session ends unexpectedly.

• Busy detection — best-effort, via NVML's per-process GPU utilization (not point-in-time; reads a short recent window so brief gaps between tokens don't misread as idle). Requires no changes to how you call Ollama — it's entirely on vram-mcp's side.

• Protection — unload()/ensure_free() refuse to evict a model that's claimed OR busy, by default. Pass force=True when you've already decided it's worth it.

Requires the nvidia-ml-py dependency (installed automatically). Falls back gracefully — claims/busy report as empty/null — on non-NVIDIA GPUs or if NVML is unavailable.

Development

pip install -e .
python -m pytest -q

The logic modules (gpu.py, ollama.py, core.py) are free of any mcp import and are fully unit-tested with mocks — no real GPU, Ollama daemon, or mcp package required to run the test suite.

Roadmap

• Other backends: AMD (ROCm/rocm-smi), Intel (xpu-smi).

• Other runtimes: vLLM, llama.cpp.

License

MIT © 2026 sushiHex