# soif-mcp

> soif-mcp — unchained-labs-soif-mcp. Use this tool when you need to estimate the water footprint of large language models (LLMs) and compare their environmental impact. The soif-mcp server takes LLM usage data as input and outputs water cost estimates, enabling informed decisions about model selection and usage. Ideal for AI developers and researchers seeking to reduce the environmental footprint of their models.

Canonical page: https://skillsregistry.net/skills/unchained-labs-soif-mcp  
JSON: https://api.skillsregistry.net/v1/skills/unchained-labs-soif-mcp

## Description

MCP server for estimating the water footprint of LLM usage and comparing models by water cost.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-09-04

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-04

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/q2fh4nd9fs)
- **Repository:** <https://github.com/Unchained-Labs/soif-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "unchained-labs-soif-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/unchained-labs-soif-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/unchained-labs-soif-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt