codex-app-server-mcp
Related Servers
Alternatives to codex-app-server-mcp
No user-submitted related servers found.
Related Servers
- AlicenseAqualityBmaintenanceLocal MCP bridge that lets Codex operate local Claude Code sessions, including listing, starting, resuming, forking, prompting, and stopping conversations via the Remote Control CLI.14MIT
- AlicenseAqualityCmaintenanceA stdio MCP server that lets Codex Desktop/CLI delegate implementation tasks to Claude Code CLI with workspace validation, Git status checks, and session resume capabilities.24MIT
- AlicenseNot gradedqualityAmaintenanceA local stdio MCP server that lets any MCP client start a Codex thread and continue it by opaque thread ID through the codex and codex-reply tools, with fail-closed sandboxing and approval policies. It restores the removed Codex CLI MCP integration by bridging clients like OpenCode to the official Codex SDK.MIT
- AlicenseAqualityBmaintenanceEnables Claude Code or any MCP client to delegate hands-on coding work to OpenAI Codex over a persistent app-server process, keeping long-lived threads with follow-ups, async polling, approvals, steering, and interrupts. Supports native code review, resuming existing sessions, structured output, and parallel worktree-isolated tasks.1024 npm1MIT
- AlicenseNot gradedqualityCmaintenanceWraps the Codex engine in a local stdio MCP server so any MCP-capable agent can run coding turns as tools, with blocking runs, start/poll progress, command approvals, interrupts, thread resume, and token usage. It also supports custom OpenAI-compatible providers, letting teams blocked by signup, payment, or network limits still use the engine.25 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients and external AI supervisors to oversee and steer native Codex sessions through a thin local stdio bridge. It exposes eleven codex_* supervisory tools for tasks such as listing threads, starting turns, observing progress, steering, responding to approvals, interrupting, checkpointing, and rolling over work.MIT
TDQS
Scored across 10 tools
Each tool maps to a distinct Codex operation: start, status, cancel, steer, review, compact, pending input, answer input, model listing, and diagnostics. Even similar actions like codex_steer and codex_answer_input are cleanly separated by their stated purpose.
The codex_ prefix and snake_case style are consistent throughout, making the family easy to recognize. Minor deviations exist: codex_models and codex_status are noun-like rather than verb_noun, while most others follow an action-oriented pattern.
Ten tools is a well-scoped set for managing Codex tasks and app-server operations. Each tool covers a meaningful lifecycle or capability without unnecessary redundancy.
The surface covers the main task lifecycle: start, monitor, cancel, steer, answer pending input, compact context, and review. Minor gaps exist around broader thread history or explicit thread deletion, but these are not essential for the core workflow.