Multi-CLI MCP

An MCP server that lets Claude, Gemini, and Codex call each other as tools.

Claude: "Hey Gemini, what do you think about this code?"
Gemini: "It's mass. Let me ask Codex for a second opinion."
Codex:  "You're both wrong. Here's the fix."

---

One-Line Install

curl -fsSL https://raw.githubusercontent.com/osanoai/multicli/main/install.sh | bash

Detects which AI CLIs you have installed and configures Multi-CLI for all of them automatically. No config files, no API keys, no environment variables. If it's on your PATH, it works.

---

What It Does

Multi-CLI sits between your AI clients and bridges them via the Model Context Protocol. Install it once, and whichever AI you're talking to gains the ability to call the others.

• Claude can ask Gemini or Codex for help
• Gemini can delegate to Claude or Codex
• Codex can consult Claude or Gemini
• Each client's own tools are hidden (no talking to yourself, that's weird)
• Auto-detects which CLIs you have installed — only shows what's available

---

The Meta Part

This tool was built by the very AIs it connects.

Claude, Gemini, and Codex wrote the code. Claude, Gemini, and Codex maintain it. Every night, a CI job queries the latest stable release of each CLI for its current model list, diffs the results against what's in the repo, and automatically publishes a new version if anything changed. New model releases get picked up within 24 hours. Deprecated models get cleaned out. The repo stays current without anyone touching it.

Because all install commands use @latest, your MCP client pulls the newest version every time it starts — no manual updates, no stale model lists, no maintenance.

Most MCP tools go stale within weeks. This one is self-maintaining by design.

---

Prerequisites

You need Node.js >= 20 and at least two of these CLIs installed:

CLI	Install
Claude Code	npm install -g @anthropic-ai/claude-code
Gemini CLI	npm install -g @google/gemini-cli
Codex CLI	npm install -g @openai/codex

Why two? Because one AI talking to itself is a monologue, not a collaboration.

---

Manual Installation

Prefer to install per-client yourself? Each command is one line.

Claude Code

claude mcp add --scope user Multi-CLI -- npx -y @osanoai/multicli@latest

Claude Desktop (JSON config)

Add to ~/Library/Application Support/Claude/claude_desktop_config.json on macOS:

{
  "mcpServers": {
    "Multi-CLI": {
      "command": "npx",
      "args": ["-y", "@osanoai/multicli@latest"]
    }
  }
}

Restart Claude Desktop completely after saving.

---

Gemini CLI

gemini mcp add --scope user Multi-CLI npx -y @osanoai/multicli@latest

Manual config (~/.gemini/settings.json)

{
  "mcpServers": {
    "Multi-CLI": {
      "command": "npx",
      "args": ["-y", "@osanoai/multicli@latest"]
    }
  }
}

---

Codex CLI

codex mcp add Multi-CLI -- npx -y @osanoai/multicli@latest

Manual config (~/.codex/config.toml) or pass --mcp-config

codex --mcp-config mcp.json

Where mcp.json contains:

{
  "mcpServers": {
    "Multi-CLI": {
      "command": "npx",
      "args": ["-y", "@osanoai/multicli@latest"]
    }
  }
}

---

Any Other MCP Client

Multi-CLI uses standard stdio transport. If your client supports MCP, point it at:

npx -y @osanoai/multicli@latest

---

Available Tools

Once connected, your AI client gains access to tools for the other CLIs (never its own):

Tool	Description
List Gemini Models	List available Gemini models and their strengths
Ask Gemini	Ask Gemini a question or give it a task
Fetch Chunk	Retrieve chunked responses from Gemini
Gemini Help	Get Gemini CLI help info
List Codex Models	List available Codex models
Ask Codex	Ask Codex a question or give it a task
Codex Help	Get Codex CLI help info
List Claude Models	List available Claude models
Ask Claude	Ask Claude a question or give it a task
Claude Help	Get Claude Code CLI help info

---

Usage Examples

Once installed, just talk naturally to your AI:

"Ask Gemini what it thinks about this architecture"
"Have Codex review this function for performance issues"
"Get Claude's opinion on this error message"
"Use Gemini to analyze @largefile.js"

Or get a second opinion on anything:

"I want three perspectives on how to refactor this module —
 ask Gemini and Codex what they'd do differently"

---

How It Works

┌─────────────┐     MCP (stdio)      ┌──────────────┐     CLI calls    ┌─────────────┐
│  Your AI    │ ◄──────────────────► │  Multi-CLI   │ ───────────────► │ Other AIs   │
│  Client     │                      │   server     │                  │ (CLI tools) │
└─────────────┘                      └──────────────┘                  └─────────────┘

1. Your AI client connects to Multi-CLI via MCP
2. Multi-CLI detects which CLIs are installed on your system
3. It registers tools for the OTHER clients (hides tools for the calling client)
4. When a tool is called, Multi-CLI executes the corresponding CLI command
5. Results flow back through MCP to your AI client

---

Troubleshooting

"No usable AI CLIs detected" Make sure at least one other CLI is installed and on your PATH:

which gemini && which codex && which claude

No tools showing up? If only your own CLI is installed, Multi-CLI hides it (no self-calls). Install a different CLI to enable cross-model collaboration.

MCP server not responding?

1. Check that Node.js >= 20 is installed
2. Run npx @osanoai/multicli@latest directly to see if it starts
3. Restart your AI client completely

---

Development

git clone https://github.com/osanoai/multicli.git
cd multicli
npm install
npm run build
npm run dev