# multi-agent-mcp

> Use this tool when you need to manage multiple AI CLI instances in parallel, executing tasks simultaneously across different agents like Claude Code, Codex, Gemini, and Cursor. It solves problems of manual instance management and sequential task execution, streamlining workflows with optional git worktree support. The tool takes AI agent inputs and task assignments, outputting managed tmux sessions for efficient parallel processing.

Canonical page: https://skillsregistry.net/skills/shiiman-multi-agent-mcp  
JSON: https://api.skillsregistry.net/v1/skills/shiiman-multi-agent-mcp

## Description

Manages multiple AI CLI instances (Claude Code, Codex, Gemini, Cursor) in tmux sessions for parallel task execution, with optional git worktree support.

## Trust

- **Trust score (0–1):** 0.00
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/reehcijbkv)
- **Repository:** <https://github.com/shiiman/multi-agent-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": "shiiman-multi-agent-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/shiiman-multi-agent-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/shiiman-multi-agent-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