# pal-mcp-server-multi-model-orchestration

The pal-mcp-server-multi-model-orchestration skill uses PAL MCP to bring multiple AI models into code reviews, debugging, and planning. Use it when you want another model to inspect a change.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 227 installs · ★ 9 repo stars
- Author: reason-machines
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/mcp-skills/tree/HEAD/skills/pal-mcp-server-multi-model-orchestration/SKILL.md
- Updated: 2026-10-09
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/pal-mcp-server-multi-model-orchestration

## What it does

The skill routes work through PAL MCP to models such as Gemini, OpenAI, Grok, and Ollama. Its `pal` tool supports model conversations, while `clink` starts external command-line AI tools as subagents with separate context. Code review has its own workflow, with confidence tracking and checks across models.

Running PAL MCP requires Python 3.10+, Git, and the `uv` package manager. At least one provider API key is needed; the README describes Ollama as an option for local models without a key. Cloud models won’t run without a configured key for a provider.

The skill supports Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode. Installing the skill and setting up PAL MCP are separate tasks. For the server, the README gives a clone-and-run method using `./run-server.sh`, or a configuration option using `uvx`.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill pal-mcp-server-multi-model-orchestration -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/pal-mcp-server-multi-model-orchestration/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/pal-mcp-server-multi-model-orchestration/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill pal-mcp-server-multi-model-orchestration -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/pal-mcp-server-multi-model-orchestration/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill pal-mcp-server-multi-model-orchestration -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/pal-mcp-server-multi-model-orchestration/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/mcp-skills skills/pal-mcp-server-multi-model-orchestration
```

2. **Manually: put the files in place**
- File: `.github/skills/pal-mcp-server-multi-model-orchestration/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill pal-mcp-server-multi-model-orchestration -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/mcp-skills --path skills/pal-mcp-server-multi-model-orchestration
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/pal-mcp-server-multi-model-orchestration/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/mcp-skills --skill pal-mcp-server-multi-model-orchestration -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/mcp-skills/tree/HEAD/skills/pal-mcp-server-multi-model-orchestration/SKILL.md

## When to use it
- ask several models to inspect code changes
- investigate an error through an isolated CLI session
- compare model opinions before choosing an API design
- assign a code review to a model acting as reviewer

## Example prompts
- Ask Gemini and GPT-5 to review the changes in the authentication module.
- Use Codex in an isolated context to investigate the memory leak.
- Compare Gemini Pro and GPT-5 on whether this API should use REST or GraphQL.

## Similar
- [edict-multi-agent-orchestration](https://affpapa.org/en/nevibecode/skills/edict-multi-agent-orchestration.md) — skill · 1400 installs
- [open-multi-agent-orchestration](https://affpapa.org/en/nevibecode/skills/open-multi-agent-orchestration.md) — skill · 718 installs
- [skypilot-multi-cloud-orchestration](https://affpapa.org/en/nevibecode/skills/skypilot-multi-cloud-orchestration.md) — skill · 1100 installs
- [multi-agentic-threat-model](https://affpapa.org/en/nevibecode/skills/multi-agentic-threat-model.md) — skill · 188 installs
- [Multi-Agent Architect](https://affpapa.org/en/nevibecode/skills/multi-agent-architect.md) — skill · 162 installs
- [deep-agents-orchestration](https://affpapa.org/en/nevibecode/skills/deep-agents-orchestration.md) — skill · 17100 installs

From the same set: [reason-machines/mcp-skills](https://affpapa.org/en/nevibecode/by/reason-machines/mcp-skills.md) — 98 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
