# mcp-fusion

> mcp-fusion — chungkung-mcp-fusion. Use this tool when you need to visually orchestrate AI workflows offline, supporting various input/output interfaces such as stdio, SSE, and Streamable HTTP. It solves problems related to managing complex AI workflows, providing a seamless and efficient way to connect and execute tasks. Ideal for use cases requiring secure, offline workflow management, such as data science and machine learning projects.

Canonical page: https://skillsregistry.net/skills/chungkung-mcp-fusion  
JSON: https://api.skillsregistry.net/v1/skills/chungkung-mcp-fusion

## Description

Visual AI workflow orchestration desktop app for MCP connect, execute. 100% offline. Supports stdio / SSE / Streamable HTTP. Built with Tauri + Rust + React.

## Trust

- **Trust score (0–1):** 0.89
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** AGPL-3.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/chungkung/mcp-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": "chungkung-mcp-fusion"
    }
  }
}
```

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