A
licenseNot graded
qualityD
maintenanceLets Claude Code query multiple AI models (Gemini, Grok, ChatGPT, DeepSeek) for diverse perspectives, code reviews, debates, and more.
MIT
codex-claude-council
Related Servers
Alternatives to codex-claude-council
- AlicenseBqualityDmaintenanceAn open-source MCP server that connects your IDE or AI assistant to the Codex CLI, enabling non-interactive automation with codex exec, safe sandboxed edits with approvals, and large-scale code analysis via @ file references.824 npmMIT
- AlicenseAqualityDmaintenanceEnables adversarial collaboration between Claude and GPT for automated code critique, verification, and multi-round debate to improve output quality.3MIT
Related Servers
- 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.5344 npmMIT
- AlicenseNot gradedqualityDmaintenanceConnects Claude Code with multiple AI models (Gemini, Grok-3, ChatGPT, DeepSeek) simultaneously, allowing users to get diverse AI perspectives, conduct AI debates, and leverage each model's unique strengths.154MIT
- 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.61,265 npm647ISC
- AlicenseNot gradedqualityBmaintenanceEnables two-way collaboration between Claude Code and the Codex CLI: Claude can hand off plans for execution or adversarial review, while the working agent can block to ask Claude questions, report progress or findings, and receive mid-run corrections. Supports multiple named, resumable sessions per project with configurable model, effort, and sandbox settings.20 npmMIT
- AlicenseAqualityBmaintenanceEnables adversarial code review by connecting Claude Code to OpenAI Codex, iterating until consensus is reached between the two AI models.35 npm1MIT
- AlicenseNot gradedqualityDmaintenanceEnables Claude Code to query ChatGPT for second opinions and compare responses between models.11 npmMIT
TDQS
A4.4/5.0
Scored across 8 tools
Disambiguation4/5
The tools have largely distinct purposes and the descriptions actively cross-reference each other (single-model asks vs. cross-check vs. transcript vs. self-participation vs. async polling vs. cancel). The main subtlety is council_ask vs council_debate, which run the same council but return the answer versus the full transcript—an agent could occasionally pick the wrong one, though descriptions clarify the tradeoff.
Naming Consistency4/5
All tools share a consistent council_ namespace prefix in snake_case, and follow an action-focused pattern (council_ask, council_join, council_turn, council_result, council_cancel). Minor irregularity: council_ask_codex / council_ask_claude use a model suffix while the combined council_ask does not, but the scheme is still readable and predictable.
Tool Count5/5
Eight tools is well within the ideal range for this domain. Each earns its place: the three ask variants for single/cross-checked answers, debate for transcripts, join/turn for self-participation, and result/cancel for the async job lifecycle.
Completeness4/5
The surface covers the full lifecycle: starting single- and dual-model jobs, participating as a model yourself, polling long-running jobs, and cancelling them. The only minor gap is no way to enumerate or list previously started jobs/sessions, but result and cancel let agents recover and manage state adequately.
Maintenance
ActivityActive
ResponsivenessNo issues