pal-mcp-server
The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model / All Of The Above] working as one.
PAL MCP Server (Provider Abstraction Layer) is an MCP server that connects AI coding assistants to multiple AI models simultaneously, enabling multi-model orchestration within a single conversation. It allows tools like Claude Code, Gemini CLI, Codex CLI, and Cursor to delegate tasks to different models—Gemini, OpenAI, Anthropic, Grok, Azure, Ollama, and others—while maintaining conversation continuity across models. The server features specialized tools for code review, debugging, planning, and collaborative decision-making, plus a CLI bridge that spawns isolated AI subagents for parallel investigations without polluting the main context window.
Key Features
Use Cases
- 01Multi-model code reviews where Claude orchestrates Gemini Pro and O3 to produce consensus feedback with severity levels
- 02Spawning specialized subagents for isolated tasks like security audits or architecture planning without cluttering main context
- 03Extended thinking and debugging with models offering large context windows (Gemini 1M tokens, O3 200K tokens)
- 04Pre-commit validation workflows that analyze changes across multiple AI perspectives before merging
- 05Collaborative architecture decisions using consensus tool to get expert opinions from multiple models
- 06API documentation lookups that force current-year reference checks to prevent outdated training data responses
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
pal-mcp-server — FAQ
What is PAL MCP Server?+
PAL MCP Server is a Model Context Protocol server that connects AI coding assistants (Claude Code, Gemini CLI, Codex CLI, Cursor) to multiple AI model providers, enabling orchestration of different models within a single conversation with full context continuity.
How do I install PAL MCP Server?+
Clone the repository and run the automated setup script (./run-server.sh), or use uvx for instant setup by adding the server configuration to your MCP client's settings file. The setup script automatically configures Claude Desktop, Claude Code, Gemini CLI, Codex CLI, and Qwen CLI.
Which AI clients work with PAL MCP Server?+
PAL works with Claude Code, Gemini CLI, Codex CLI, Qwen Code CLI, Claude Desktop, Cursor, and the Claude Dev VS Code extension. Any MCP-compatible client can use it.
What API keys do I need?+
You need at least one API key from your chosen providers: OpenRouter (multi-model access), Google AI (Gemini), OpenAI (GPT/O3), Azure OpenAI, X.AI (Grok), or DIAL. Ollama requires no API key for local models. Configure keys in your .env file or MCP client settings.
Is PAL MCP Server free?+
The PAL MCP Server itself is free and open-source (Apache 2.0). However, API costs apply when using cloud providers like OpenAI, Gemini, or OpenRouter. Local models via Ollama are completely free.
What are the prerequisites for running PAL?+
You need Python 3.10 or higher, Git, and uv package manager installed. At least one AI model provider API key is required unless you only use local Ollama models.
How do I install pal-mcp-server?+
Open the source repository on GitHub and follow its README. pal-mcp-server is a mcp server — MCP Agents Market links you directly to the official repo.
Is pal-mcp-server free?+
pal-mcp-server is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.