codex-advisor
Related Servers
Alternatives to codex-advisor
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityAmaintenanceEnables Claude Desktop users to get second opinions and answers from ChatGPT through the Codex CLI, including document reviews with optional focus/rubric and question answering with context.10 npmMIT
- FlicenseNot gradedqualityAmaintenanceLets Claude Code's active model request a second opinion from a separately configured external model over any OpenAI-compatible chat-completions endpoint or a custom command adapter, returning advisory text and a list of available profiles. It is intended for high-impact decisions and complex debugging, without scanning repositories, replacing the main model, or automatically sending diffs.-
- AlicenseAqualityAmaintenanceLets coding agents such as Claude Code, Kiro CLI, and Antigravity CLI call the locally installed Codex CLI as an independent debate partner, with per-question model and reasoning-effort selection. Supports asynchronous polling of long replies, cancellation of a turn, read-only project exploration, and resuming saved conversations in later sessions.5381 npm1MIT
- AlicenseAqualityDmaintenanceBridges Claude and OpenAI's Codex CLI for AI-powered code analysis, generation, and review, with support for session management, web search, and structured output.61,539 npm647ISC

LLM Council MCPofficial
AlicenseNot gradedqualityDmaintenanceEnables Claude Code to consult external LLMs (GPT, Gemini) through multi-turn sessions for second opinions, parallel consultations, and web-grounded research.MIT- AlicenseAqualityCmaintenanceEnables any MCP-capable coding agent to request an independent, read-only second opinion from a stronger model at consequential decision points such as planning, debugging, risk review, and handoff. It exposes consult, session-state, reset, and health tools over stdio or authenticated Streamable HTTP, with explicit context, structured validated advice, session continuity, call budgets, and secret redaction.5MIT
TDQS
Scored across 2 tools
The two tools are completely distinct: one performs a consultation, the other manages configuration. No overlap or ambiguity exists between them.
Tool names use different patterns: 'consult_advisor' follows verb_noun, while 'advisor_config' is noun_noun. The inconsistency is noticeable but both names are clear and self-explanatory.
With only 2 tools, the set feels thin but is appropriate for the narrow scope of advisor consultation and configuration. It covers the essential actions without unnecessary bloat.
The domain of consulting and configuring an advisor is well-covered. A minor gap is the lack of consultation history or logging, but for the stated purpose (strategic guidance and settings) the surface is essentially complete.