Nexus Mcp

j7an/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.

GitHub stars

3

tool

1

transport

STDIO

last updated

Oct 24, 2026

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

uvx --with 'nexus-mcp[all]' nexus-mcp          # run directly
pip install 'nexus-mcp[claude]'                 # or install
pip install 'nexus-mcp[codex]'                  # Codex only
pip install 'nexus-mcp[antigravity]'

{ "mcpServers": { "nexus": { "command": "uvx", "args": ["--with", "nexus-mcp[all]", "nexus-mcp"] } } }