io.github.arose26/gguf-mcp
gguf
Inspect local GGUF/safetensors models: quantization, params, VRAM fit — headers only.
alive probed 2026-10-15
4tools
1.0ktokens in Claude Opus 5.5
1.0ktokens in Claude Code
0.5 %of a 200k context window
592o200k_base estimate
385 msto initialize
8 msto list tools
- Run it
- npx -y gguf-mcp@0.1.1 (stdio, probed in a container with the network off)
- Host
- npmjs.com
- Reports itself as
- gguf 0.1.0
- Capabilities
- tools
- Instructions
- none
- Claude count
- Claude Opus 5.5, measured 2026-10-15. Counted again when the tool definitions change. Method.
- Repository
- https://github.com/arose26/gguf-mcp
- Registry
- active, updated 2026-08-14 · registry entry
- Reachable
- 1 of the last 1 probe
Most expensive tools
| Tool | Tokens (o200k) | Share of this server |
|---|---|---|
| get_metadata | 159 | 27 % |
| list_tensors | 153 | 26 % |
| estimate_vram | 144 | 24 % |
| inspect_model | 136 | 23 % |
Badge and feed
[](https://mcpcost.ulehla.dev/s/io.github.arose26/gguf-mcp)
An entry for every probe that changed the result, the tool count or the token cost: Atom feed. Add it to a feed reader or a Slack RSS app to hear when the server stops answering or its tool set grows.