PAL MCP Server

Stale
GitHub Python NOASSERTION

Description

PAL MCP Server unifies Claude Code, GeminiCLI, and CodexCLI with multiple LLM providers (Gemini, OpenAI, OpenRouter, Azure, Grok, Ollama, and custom models) into a single collaborative MCP service.

Key Features

  • Multi-model orchestration: Claude Code coordinates with Gemini Pro, GPT-5, O3, and 50+ other models within a single prompt
  • CLI-to-CLI bridge (clink): spawn isolated subagent CLIs for code review, planning, and task delegation without polluting main context
  • Conversation threading across models: full context carries forward seamlessly between tools and models for complex multi-step workflows
  • Extended context windows: delegate massive codebases to Gemini (1M tokens) or O3 (200K tokens) beyond Claude's native limits
  • Context revival: even after Claude's context resets, other models can remind it of prior discussions without re-ingesting documents
  • Professional multi-pass code reviews with severity levels, confidence tracking, and consensus from multiple AI experts

Use Cases

💡 Multi-model collaborative code review with automated planning, implementation, and pre-commit validation
💡 Cross-model debate to reach deeper insights on architectural decisions and design trade-offs
💡 Context recovery across long-running sessions using external models as persistent memory bridges
💡 Role-specialized subagent delegation: spawn planner, code reviewer, or custom agents with specialized prompts

Tags

mcp multi-model claude-code llm agent

Categories

🔌 MCP Tools

Quick Start

Install PAL MCP via your package manager, configure it as an MCP server in Claude Code or your preferred CLI tool, then use natural language to orchestrate multiple models. Example: 'Perform a codereview using gemini pro and o3 and use planner to generate a detailed plan, implement the fixes and do a final precommit check.'
Visit GitHub

Related Projects