Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
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.
11.5kstars
998forks
Python
Quality signals
StaleNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
Unified AI orchestration layer that lets you switch between multiple AI models (Gemini, GPT, Claude, etc.) seamlessly within a single CLI session for complex dev workflows.
Use this when
- Debugging large codebases with multiple AI models
- Running isolated code reviews in fresh contexts
- Switching models mid-task without losing conversation history
- Collaborative debugging with model-specific strengths
- Bypassing CLI token limits via model delegation
Don't use when
- Need deterministic, repeatable outputs
- Working offline with no model access
- Handling sensitive code you can't share with external APIs
Capabilities
- Multi-model orchestration in single CLI session
- CLI-to-CLI bridge for isolated subagent workflows
- Conversation continuity across model switches
- Automatic model selection per subtask
- Context revival after CLI context resets
- Role specialization with custom system prompts
InstallMCPInstall as a Claude Code skill
Universal installANY TOOL
$ npx skillcity@latest BeehiveInnovations/pal-mcp-serverAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor, Cline, OpenCode, Gemini CLI, Anti-Gravity, OpenClaw and Hermes.
Requires Node.js 18+ (ships with npx).
Or install manually
# Install into ~/.claude/skills/ mkdir -p ~/.claude/skills/pal-mcp-server curl -fsSL https://raw.githubusercontent.com/BeehiveInnovations/pal-mcp-server/main/README.md -o ~/.claude/skills/pal-mcp-server/SKILL.md
Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
pal-mcp-server — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt