Nexus Mcp

Wraps Codex, Claude Code, and OpenCode CLI agents as MCP tools so you can call them from inside another AI session. The main hook is batch_prompt, which fans out requests to multiple agents in parallel with configurable concurrency and automatic retries. You get seven tools for invoking agents and managing preferences, four resources that expose runner metadata and model tiers, and ten prompt templates for common workflows like code review or research synthesis. Useful when you want a second opinion from a different model without switching contexts, or when you need to query multiple agents at once and aggregate their answers. Persistent preferences survive across sessions if you wire up a file or Redis store instead of the default in memory backend.