A
licenseNot graded
qualityB
maintenanceEnables delegating bounded tasks from Codex to Claude Code, including read-only reviews, isolated branch edits, long-running background work, and approval handling.
220 npm
MIT
codex-claude-mcp
by NtTestAlert
Related Servers
Alternatives to codex-claude-mcp
No user-submitted related servers found.
Related Servers
- AlicenseNot gradedqualityBmaintenanceEnables Codex to delegate tasks to interactive Claude Code sessions as role-controlled subagents for exploration, code review, and implementation, using the existing Claude Code installation on macOS.MIT
- AlicenseAqualityDmaintenanceEnables OpenAI Codex to consult Claude Code for co-analysis, adversarial second opinions, and read-only file review over the Model Context Protocol, with Claude remaining advisory and unable to modify files.912 npmMIT
- AlicenseNot gradedqualityAmaintenanceEnables Claude Code and OpenAI Codex to exchange messages directly within their sessions, including optional cross-review of plans, without copying between terminals.77 npmMIT
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- 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.43 npmMIT
TDQS
A4/5.0
Scored across 2 tools
Disambiguation5/5
The two tools are cleanly separated by lifecycle stage: claude_ask starts a new session and claude_followup continues an existing one. There is no plausible confusion about which to call for a given intent.
Naming Consistency5/5
Both names share the identical 'claude_' prefix in snake_case and use parallel action suffixes (ask/followup). The convention is applied uniformly across the entire surface.
Tool Count3/5
Two tools is thin even for a narrow delegation server; only the start/continue pair exists. A focused purpose partly justifies it, but it sits at the borderline of minimalism.
Completeness3/5
The core start-and-continue workflow is covered, but there is no way to list, inspect, or terminate sessions, and no status/result-retrieval operation. These are notable lifecycle gaps for session management.
Maintenance
ActivityMaintained
ResponsivenessNo issues