PAL MCP Server

What it does

• Multi-model MCP server (PAL): let Claude consult Gemini/other models for second opinions, code review, debugging
• Tools like `chat`, `codereview`, `debug`, `analyze` route prompts to configured external models
• `DEFAULT_MODEL=auto` picks per-task; `DISABLED_TOOLS` trims the surface
• `run-server.sh` auto-configures Claude Desktop, Claude Code, Gemini CLI, Codex CLI, Qwen CLI

When to use it

When you want Claude to cross-check its own reasoning against another model — e.g. send a diff to Gemini for review before committing, or brainstorm with a different model's perspective.

Getting started

Option A (recommended): clone and auto-setup:

git clone https://github.com/BeehiveInnovations/pal-mcp-server.git
cd pal-mcp-server
./run-server.sh

Option B, uvx in mcpServers:

{
  "pal": {
    "command": "bash",
    "args": ["-c", "for p in $(which uvx 2>/dev/null) $HOME/.local/bin/uvx /opt/homebrew/bin/uvx /usr/local/bin/uvx uvx; do [ -x \"$p\" ] && exec \"$p\" --from git+https://github.com/BeehiveInnovations/pal-mcp-server.git pal-mcp-server; done; echo 'uvx not found' >&2; exit 1"],
    "env": {
      "GEMINI_API_KEY": "your-key-here",
      "DEFAULT_MODEL": "auto"
    }
  }
}

Things to know

Every consultation is a paid external API call (Gemini etc.) — prompts and code leave your machine. `run-server.sh` rewrites client configs, so review what it changed if you manage configs by hand.