# Nodegrove VRAM: can I run it? (remote · mcp.nodegrove.io)

Can this LLM run on my GPU? VRAM, speed ceiling and what fits instead, for any model and GPU.

- Trust score: 74/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-22

## Components

- remote · `mcp.nodegrove.io`: 74/100 (this document), [markdown](https://verifymcp.io/servers/io-nodegrove-vram-mcp/mcp.md), [page](https://verifymcp.io/servers/io-nodegrove-vram-mcp/mcp)
- npm · `@nodegrove/vram-mcp`: 76/100, [markdown](https://verifymcp.io/servers/io-nodegrove-vram-mcp/nodegrove-vram-mcp.md), [page](https://verifymcp.io/servers/io-nodegrove-vram-mcp/nodegrove-vram-mcp)

## Channel facts

- Endpoint: `https://mcp.nodegrove.io/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.4`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-22.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1578 tokens (~263/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 63/100
  - Stability observed for 19 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Nodegrove VRAM: can I run it? MCP server?

Nodegrove VRAM: can I run it? is a hosted endpoint at https://mcp.nodegrove.io/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http io-nodegrove-vram-mcp 'https://mcp.nodegrove.io/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "io-nodegrove-vram-mcp": {
      "url": "https://mcp.nodegrove.io/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "io-nodegrove-vram-mcp": {
      "type": "http",
      "url": "https://mcp.nodegrove.io/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.io-nodegrove-vram-mcp]
url = "https://mcp.nodegrove.io/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-nodegrove-vram-mcp": {
      "type": "remote",
      "url": "https://mcp.nodegrove.io/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-nodegrove-vram-mcp --url 'https://mcp.nodegrove.io/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-nodegrove-vram-mcp:
    url: "https://mcp.nodegrove.io/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "io-nodegrove-vram-mcp": {
      "Transport": "http",
      "Url": "https://mcp.nodegrove.io/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add io-nodegrove-vram-mcp -t streamable-http -u 'https://mcp.nodegrove.io/mcp'
```

### Other

```json
{
  "mcpServers": {
    "io-nodegrove-vram-mcp": {
      "type": "http",
      "url": "https://mcp.nodegrove.io/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-22 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-19 (score 73, +1)

- [functional] Server version: 1.1.3 → 1.1.4

### 2026-10-17 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-16 (score 71, 0)

- [security] Tool “list_models” rewrote its description, which is the text the model reads
- [functional] Server version: 1.1.2 → 1.1.3

### 2026-10-15 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-13 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-12 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 30. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-10 (score 68, +1)

- [security] Tool “list_models” rewrote its description, which is the text the model reads
- [functional] Server version: 1.1.1 → 1.1.2

## MCP tools (6)

### `can_i_run` (~480 tokens)

Can I run it?

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 that fits and, on a no, every change that would make it fit: quantisation, KV cache, context, another card or a smaller model. Model: a name or id from list_models, any Hugging Face repo id, or its architecture. GPU: a name or id from list_gpus, or vram_gb for any other card.

Input parameters:

- `active_params_b` (number): Parameters read per token, billions, for a mixture-of-experts model read from Hugging Face (from its model card). Sets the speed ceiling.
- `apple_silicon` (boolean): vram_gb is Apple unified memory; the GPU can use about 75% of it by default.
- `architecture` (object): A model described by its config.json values instead of a name.
- `bandwidth_gb_s` (number): Memory bandwidth from the maker's spec, GB/s, for a speed ceiling.
- `context` (integer): Tokens held in context: prompt plus conversation.
- `gpu` (string): A GPU from list_gpus (id or name, e.g. "rtx-4090", "4090" or "M4 Max").
- `kv_cache` (string): KV cache precision. fp16 is what most runtimes use; q8 halves the cache.
- `model` (string): A model from list_models (id or name, e.g. "llama-3.3-70b" or "Llama 3.3 70B"), or any Hugging Face repo id (e.g. "Qwen/Qwen3-8B"), read live from its config.json.
- `quant` (string): Weight quantisation: fp16 (FP16 / BF16), q8 (Q8_0), q6 (Q6_K), q5 (Q5_K_M), q4 (Q4_K_M), q3 (Q3_K_M). q4 is the common default.
- `vram_gb` (number): Memory of a card not in list_gpus, GB. For a Mac, its unified memory with apple_silicon: true.

### `what_fits` (~298 tokens)

What fits my GPU?

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 that fits with room for context at conversational speed), the largest that fits, the best at Q8 and the first out of reach. GPU: a name or id from list_gpus, or vram_gb for any other card.

Input parameters:

- `apple_silicon` (boolean): vram_gb is Apple unified memory; the GPU can use about 75% of it by default.
- `bandwidth_gb_s` (number): Memory bandwidth from the maker's spec, GB/s, for a speed ceiling.
- `context` (integer): Tokens held in context: prompt plus conversation.
- `gpu` (string): A GPU from list_gpus (id or name, e.g. "rtx-4090", "4090" or "M4 Max").
- `quant` (string): Weight quantisation: fp16 (FP16 / BF16), q8 (Q8_0), q6 (Q6_K), q5 (Q5_K_M), q4 (Q4_K_M), q3 (Q3_K_M). q4 is the common default.
- `vram_gb` (number): Memory of a card not in list_gpus, GB. For a Mac, its unified memory with apple_silicon: true.

### `estimate_vram` (~312 tokens)

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 each. Model: a name or id from list_models, any Hugging Face repo id, or its architecture (params_b, layers, kv_heads, head_dim).

Input parameters:

- `active_params_b` (number): Parameters read per token, billions, for a mixture-of-experts model read from Hugging Face (from its model card). Sets the speed ceiling.
- `architecture` (object): A model described by its config.json values instead of a name.
- `context` (integer): Tokens held in context: prompt plus conversation.
- `kv_cache` (string): KV cache precision. fp16 is what most runtimes use; q8 halves the cache.
- `model` (string): A model from list_models (id or name, e.g. "llama-3.3-70b" or "Llama 3.3 70B"), or any Hugging Face repo id (e.g. "Qwen/Qwen3-8B"), read live from its config.json.
- `quant` (string): Weight quantisation: fp16 (FP16 / BF16), q8 (Q8_0), q6 (Q6_K), q5 (Q5_K_M), q4 (Q4_K_M), q3 (Q3_K_M). Omit it for all 6.

### `estimate_from_hf_repo` (~198 tokens)

Estimate VRAM from a Hugging Face 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 latent), how much each 1,000 tokens of context costs, and weights + KV cache + overhead at every quantisation. For models nodegrove.io has not reviewed; anything the reader cannot model is listed in warnings.

Input parameters:

- `active_params_b` (number): Parameters read per token, billions, for a mixture-of-experts model read from Hugging Face (from its model card). Sets the speed ceiling.
- `context` (integer): Tokens held in context: prompt plus conversation.
- `kv_cache` (string): KV cache precision. fp16 is what most runtimes use; q8 halves the cache.
- `repo` (string, required): Hugging Face repo id, e.g. "Qwen/Qwen3-8B", or its huggingface.co URL.

### `list_models` (~85 tokens)

List models

The open-weight LLMs nodegrove.io has verified against their config.json (data version 2026-10-16): id, size, attention design, native context, licence, memory at Q4 with 8k context and each model's page.

Input parameters:

- `search` (string): Words to filter by, e.g. "qwen" or "24 GB".

### `list_gpus` (~64 tokens)

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.

Input parameters:

- `search` (string): Words to filter by, e.g. "qwen" or "24 GB".

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/io-nodegrove-vram-mcp/mcp#diagnostics

## Score history

- 2026-10-22: 74
- 2026-10-21: 73
- 2026-10-20: 73
- 2026-10-19: 73
- 2026-10-18: 72
- 2026-10-17: 72
- 2026-10-16: 71
- 2026-10-15: 71
- 2026-10-14: 70
- 2026-10-13: 70
- 2026-10-12: 69
- 2026-10-10: 68
- 2026-10-07: 67
- 2026-10-05: 66
- 2026-10-04: 66
- 2026-10-03: 65

## Common questions

### What is the Nodegrove VRAM: can I run it? MCP server?

Nodegrove VRAM: can I run it? is an MCP server listed in the public MCP registry as io.nodegrove/vram-mcp. Can this LLM run on my GPU? VRAM, speed ceiling and what fits instead, for any model and GPU. This page covers its hosted endpoint (https://mcp.nodegrove.io/mcp).

### Is the Nodegrove VRAM: can I run it? MCP server safe to use?

Nodegrove VRAM: can I run it? scores 74 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Nodegrove VRAM: can I run it? MCP server expose?

Nodegrove VRAM: can I run it? exposes 6 tools: can_i_run, what_fits, estimate_vram, estimate_from_hf_repo, list_models, list_gpus. Their descriptions and schemas cost roughly 1,437 tokens of context every time the server is loaded.

### Does the Nodegrove VRAM: can I run it? MCP server require authentication?

No. We connected to Nodegrove VRAM: can I run it? without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Nodegrove VRAM: can I run it? MCP server still maintained?

Nodegrove VRAM: can I run it? is still listed as active in the MCP registry. We last reached this channel on 22 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://mcp.nodegrove.io/mcp
- Repository: https://github.com/nodegrove/vram-mcp
- Website: https://nodegrove.io/mcp
- Changelog RSS feed: https://verifymcp.io/servers/io-nodegrove-vram-mcp/mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-nodegrove-vram-mcp/mcp.json
- HTML version of this page: https://verifymcp.io/servers/io-nodegrove-vram-mcp/mcp