# local-fusion MCP server

> Use this tool when you need to perform structured multi-model analysis and synthesis locally, enabling collaborative decision-making and data synthesis across multiple models. It solves problems of data inconsistency and model siloing by providing a unified interface for multi-model council and build/check loop tools. The local-fusion MCP server takes in Claude Code or MCP client inputs and outputs synthesized data and analysis results.

Canonical page: https://skillsregistry.net/skills/kelvincushman-local-fusion  
JSON: https://api.skillsregistry.net/v1/skills/kelvincushman-local-fusion

## Description

Exposes a multi-model council (panel-judge-synthesizer) and a build/check loop as MCP tools, enabling Claude Code or any MCP client to perform structured multi-model analysis and synthesis locally.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/oj0a7wu40i)
- **Repository:** <https://github.com/kelvincushman/local-fusion>

## 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": "kelvincushman-local-fusion"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/kelvincushman-local-fusion` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/kelvincushman-local-fusion/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