# @nodegrove/vram-mcp

MCP server: can this open LLM run on my GPU? VRAM, KV cache, speed ceilings and what would fit instead, with the exact math nodegrove.io uses. Any Hugging Face repo, any GPU.

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the package rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 1.0.0
- **Author:** Nodegrove
- **License:** (MIT AND CC-BY-4.0)
- **npm:** @nodegrove/vram-mcp
- **Endpoints:** streamable-http https://mcp.nodegrove.io/mcp
- **Source:** https://github.com/nodegrove/vram-mcp
- **Endpoint health:** reachable (last checked 2026-10-05T01:57:15.920Z, 1 sample) — uptime is not a security property and is not part of the trust score
- **Compatible clients:** claude-code, cursor, copilot, chatgpt, gemini (basis: transport)

## Trust

60/100 (B), scored on the package rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 0 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-10-05T01:57:01.849Z
- **Version scanned:** 1.0.0
- **CVEs:** none found by OSV at scan time

## Tools

7 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `nodegrove-vram`
- `can_i_run` — Can this GPU run this open-weight LLM? Returns fits, tight or no, the memory split (weights, KV cache, overhead), a decode-speed ceiling, the longest context th
- `what_fits` — Which open-weight LLMs fit this GPU: every model in list_models checked at one quantisation and context, with a recommended everyday model (the biggest class th
- `estimate_vram` — How much memory an LLM needs: weights + KV cache + overhead at each quantisation (or one), at a given context, and the smallest common card class that holds eac
- `estimate_from_hf_repo` — Reads any Hugging Face model repo's config.json and parameter count and estimates its memory: the attention layout found (standard, sliding-window, hybrid or la
- `list_models`
- `list_gpus` — The GPUs and machines nodegrove.io covers: memory, the memory a runtime can use and bandwidth, from the makers' specs, with each one's page.

## Install

**Verdict: review** — Installable, but 1 thing to check first: No publisher has proved control of this listing; it is indexed, not vouched for.
**Cautions** (coverage gaps and advisories — never blocking)
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"vram\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@nodegrove/vram-mcp\"\n      ]\n    }\n  }\n}"
```

## Blast radius

Contained to extensive — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs locally and hosted; read-only tool surface.
- Floor 16, ceiling 34 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/%40nodegrove%2Fvram-mcp
- Install plan: https://forgeregistry.com/api/v1/packages/%40nodegrove%2Fvram-mcp/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/%40nodegrove%2Fvram-mcp
- HTML page: https://forgeregistry.com/registry/%40nodegrove%2Fvram-mcp
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.