pal-mcp-server-multi-model-orchestration — Claude Code skill
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.
no license 227 installs ★ 9 updated 2026-10-09
npx skills add reason-machines/mcp-skills --skill pal-mcp-server-multi-model-orchestration -a claude-codeWhat pal-mcp-server-multi-model-orchestration 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.
What it helps with
- 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 for the agent
- 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.
How to install pal-mcp-server-multi-model-orchestration
1Skills CLI (Vercel)
npx skills add reason-machines/mcp-skills --skill pal-mcp-server-multi-model-orchestration -a claude-code2Manually: put the files in place
~/.claude/skills/pal-mcp-server-multi-model-orchestration/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/pal-mcp-server-multi-model-orchestration/
1Skills CLI (Vercel)
npx skills add reason-machines/mcp-skills --skill pal-mcp-server-multi-model-orchestration -a codex2Manually: put the files in place
.agents/skills/pal-mcp-server-multi-model-orchestration/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add reason-machines/mcp-skills --skill pal-mcp-server-multi-model-orchestration -a cursor2Manually: put the files in place
.cursor/skills/pal-mcp-server-multi-model-orchestration/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install reason-machines/mcp-skills skills/pal-mcp-server-multi-model-orchestration2Manually: put the files in place
.github/skills/pal-mcp-server-multi-model-orchestration/SKILL.md1Skills CLI (Vercel)
npx skills add reason-machines/mcp-skills --skill pal-mcp-server-multi-model-orchestration -a gemini-cli2Platform CLI
gemini skills install https://github.com/reason-machines/mcp-skills --path skills/pal-mcp-server-multi-model-orchestrationManually: put the files in place
.devin/skills/pal-mcp-server-multi-model-orchestration/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add reason-machines/mcp-skills --skill pal-mcp-server-multi-model-orchestration -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about pal-mcp-server-multi-model-orchestration
How do I install pal-mcp-server-multi-model-orchestration in Claude Code?
Run npx skills add reason-machines/mcp-skills --skill pal-mcp-server-multi-model-orchestration -a claude-code. The skill file is at ~/.claude/skills/pal-mcp-server-multi-model-orchestration/SKILL.md.
What does pal-mcp-server-multi-model-orchestration do?
It helps send tasks to models through PAL MCP, launch external AI CLIs with separate context, and run code reviews that check findings across models.
What do I need to run PAL MCP?
You need Python 3.10+, Git, the uv package manager, and at least one provider API key. Ollama can be used for local models without a key.