# io.github.arose26/gguf-mcp (npm · gguf-mcp)

Inspect local GGUF/safetensors models: quantization, params, VRAM fit — headers only.

- Trust score: 69/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-18

## Components

- npm · `gguf-mcp`: 69/100 (this document), [markdown](https://verifymcp.io/servers/arose26-gguf-mcp/gguf-mcp.md), [page](https://verifymcp.io/servers/arose26-gguf-mcp/gguf-mcp)

## Channel facts

- Registry: `npm`
- Package: `gguf-mcp`
- Version: `0.1.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-08-18.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 30 of 96 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 3 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 80/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 413 tokens (~103/item across 4 items; 4 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add arose26-gguf-mcp -- npx -y gguf-mcp
```

### Codex

```bash
codex mcp add arose26-gguf-mcp -- npx -y gguf-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "arose26-gguf-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "gguf-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add arose26-gguf-mcp --command npx --arg -y --arg gguf-mcp
```

### Hermes

```yaml
mcp_servers:
  arose26-gguf-mcp:
    command: "npx"
    args: ["-y", "gguf-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "arose26-gguf-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "gguf-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-08-15 (score 69)

First indexed and scored.

## MCP tools (4)

### `inspect_model` (~98 tokens)

Inspect a local model file

Summarize a local GGUF or safetensors model: architecture, parameter count, quantization, context length, file size, tensor count. Reads only headers — inspecting a 70 GB model is instant. Works on extension-less GGUF blobs (e.g. Ollama's).

Input parameters:

- `path` (string, required): Path to a .gguf or .safetensors file, a *.safetensors.index.json, or a model directory

### `list_tensors` (~97 tokens)

List tensors

Tensor names, shapes, and storage types inside a model file. Filter by substring (e.g. 'attn' or 'blk.0').

Input parameters:

- `filter` (string): Case-insensitive substring to filter tensor names
- `limit` (integer): Max tensors to return
- `path` (string, required): Path to a .gguf or .safetensors file, a *.safetensors.index.json, or a model directory

### `estimate_vram` (~100 tokens)

Estimate VRAM needed

Will this model fit? Estimates memory as exact weights size plus a modeled fp16 KV cache (GGUF; context defaults to min(model context, 8192)). Safetensors models get a weights-only figure.

Input parameters:

- `context_length` (integer): Context window to budget the KV cache for
- `path` (string, required): Path to a .gguf or .safetensors file, a *.safetensors.index.json, or a model directory

### `get_metadata` (~118 tokens)

Get model metadata

The model's metadata key-value store (GGUF) or __metadata__ block (safetensors). Large arrays arrive as {count, sample} summaries and long strings are truncated, so tokenizer vocabularies can't flood the context. Filter keys by substring (e.g. 'tokenizer' or 'rope').

Input parameters:

- `filter` (string): Case-insensitive substring to filter metadata keys
- `path` (string, required): Path to a .gguf or .safetensors file, a *.safetensors.index.json, or a model directory

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/arose26-gguf-mcp/gguf-mcp#diagnostics

## Score history

- 2026-08-18: 69
- 2026-08-17: 69
- 2026-08-16: 69
- 2026-08-15: 69

## Links

- npm package: https://www.npmjs.com/package/gguf-mcp
- Socket report: https://socket.dev/npm/package/gguf-mcp
- Repository: https://github.com/arose26/gguf-mcp
- Changelog RSS feed: https://verifymcp.io/servers/arose26-gguf-mcp/gguf-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/arose26-gguf-mcp/gguf-mcp.json
- HTML version of this page: https://verifymcp.io/servers/arose26-gguf-mcp/gguf-mcp