codex-app-mcp
Related Servers
Alternatives to codex-app-mcp
No user-submitted related servers found.
Related Servers
- AlicenseAqualityAmaintenanceA local MCP bridge that lets a compatible host start, monitor, steer, interrupt, resume, and approve Codex app-server work while enforcing repository-root security.10MIT
- 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
- FlicenseNot gradedqualityCmaintenanceEnables MCP-compatible hosts such as OpenCode to drive the Codex CLI through codex app-server over stdio, exposing tools to run prompts, inspect status, list threads, and interrupt running turns.-
- FlicenseAqualityBmaintenanceEnables MCP clients to start new Codex conversations and continue existing threads, exposing codex and codex-reply tools over stdio via the Codex app-server protocol.2-
- AlicenseNot gradedqualityCmaintenanceBridges MCP clients such as Claude Code and Cursor to independent Codex app-server sessions, letting them start, poll, steer, review, compact, cancel, and answer prompts for asynchronous Codex tasks over local stdio or a remote authenticated WebSocket. Runs read-only by default, with workspace-write sandboxing only when a user explicitly enables it, and reports job status, model listing, and progress back to the client.1MIT
- AlicenseNot gradedqualityBmaintenanceA 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
TDQS
Scored across 20 tools
Most tools have clearly distinct purposes (status, doctor, fs, events, etc.), but there is some overlap among job/lane/turn/goal management which could confuse agents about which to use for background work. Descriptions differentiate them, but boundaries are less crisp.
All tools follow a consistent codex_app_ prefix and mostly use noun-like names (status, doctor, fs, job), but a few use verbs (discover, mcp_call) and rpc_read is an adjective-noun combo. The pattern is predictable overall.
With 20 tools, this server is on the heavy side (16-25). The scope is broad enough that each tool may be justified, but the count will likely overwhelm agents and increase selection difficulty.
The tool surface is remarkably comprehensive, covering diagnostics, filesystem, events, jobs, scheduling, RPC, commands, threads, turns, goals, review, and process control. There are no obvious dead ends or missing core operations for the stated purpose of managing a Codex app-server.