zai-one

codex-app-mcp

Community zai-one
Updated

MCP server for Codex

codex-app-mcp

Version 0.4.0 — Governed MCP gateway for OpenAI Codex app-server.

This package turns a single long-lived codex app-server process into an MCPserver that other agents and IDEs can call. Codex remains the backend;codex-app-mcp is the policy-aware gateway (stdio or bearer HTTP), not areplacement for the CLI or for ChatGPT.

Security one-liner: no OAuth tokens or API keys belong in this repo.Model auth is the local Codex CLI session from codex login(CODEX_HOME). HTTP bearer is an operator-generated local secret only.

Install guides

Language Guide
English docs/install/en.md
Русский docs/install/ru.md
简体中文 docs/install/zh-CN.md
Español docs/install/es.md

Also: REFERENCE · VERIFICATION ·SECURITY · CONTRIBUTING ·MIGRATION

Capabilities

  • Threads, turns, steering, interrupt, fork, archive, and rollback
  • Autonomous persisted goals with model, reasoning effort, and token budget
  • Native review, command sessions, filesystem v2, and unsandboxed process/*
  • Approvals, user input, dynamic tools, and server-initiated requests
  • Durable SQLite jobs, worktree lanes, and timezone-aware RRULE schedules
  • Typed access to methods in the configured experimental app-server schema
  • Downstream MCP/SaaS calls with server and tool allowlists
  • Stdio MCP and bearer-protected HTTP (no unsupported WebSocket surface)
  • Exact-schema introspection, secret-safe audit, metrics, retry, and recovery

There are 20 MCP tools (including codex_app_status, codex_app_thread,codex_app_goal, codex_app_lane, codex_app_job, and more). Seedocs/REFERENCE.md.

Prerequisites

  • Python 3.10+
  • Codex CLI installed (codex on PATH, or CODEX_APP_MCP_BIN)
  • Local auth: codex login (session under CODEX_HOME)

Quick install

cd <path-to-repository>
python -m pip install -e ".[test]"

Project paths fail closed until roots are configured:

export CODEX_APP_MCP_ALLOWED_ROOTS="/path/to/allowed/project"

Quick run

Stdio (default — what most desktop MCP hosts spawn):

codex-app-mcp
# or:
python -m codex_app_mcp

HTTP (operator secret, loopback bind):

export CODEX_APP_MCP_HTTP_TOKEN="$(openssl rand -hex 32)"
codex-app-mcp --transport http --host 127.0.0.1 --port 8765

Prefer CODEX_APP_MCP_HTTP_TOKEN_FILE for services. The token env var andtoken file are mutually exclusive. Never put OpenAI/Codex OAuth into thesesettings.

Client matrix

Client Typical mode Notes
Claude Desktop stdio Config JSON with command / env — example
Claude Code stdio Project/user .mcp.json — example
Cursor stdio (or HTTP URL if supported) example
VS Code / Continue stdio Register the same command in MCP / Continue settings
Remote agents HTTP + TLS Reverse proxy or tunnel; bearer required; not native ChatGPT web stdio

ChatGPT web does not natively host local stdio MCP. Remote connectors, ifany, need a HTTPS endpoint you control—never put OpenAI credentials into theHTTP bearer config. Full details: docs/install/en.md.

First verification

python -m pytest -q
python scripts/probe_stdio.py
python scripts/probe_http.py

In a connected MCP host, call codex_app_status. Optional deeper checks:scripts/check_protocol.py, scripts/audit_protocol.py,scripts/probe_full.py.

Architecture (short)

MCP client / agent host
        │ stdio or bearer HTTP
        ▼
codex-app-mcp  (policy, jobs, lanes, audit)
        │ JSON-RPC over child stdio
        ▼
codex app-server  (threads, turns, goals, tools)
        │
        ▼
local CODEX_HOME session from `codex login`

Security

  • No API keys or OAuth material in the repository or public examples
  • Auth to Codex: local CLI session only
  • HTTP: operator-generated bearer via CODEX_APP_MCP_HTTP_TOKEN orCODEX_APP_MCP_HTTP_TOKEN_FILE (never commit)
  • Project roots fail closed; full access and unsafe RPC are separate opt-ins
  • Audit omits prompts, tokens, and credentials

Details and reporting: SECURITY.md.

Repository layout

codex_app_mcp/   runtime package
docs/            reference, verification, install (i18n)
examples/        placeholder MCP client configs
scripts/         protocol and transport probes
tests/           automated test suite
pyproject.toml   package metadata (version 0.4.0)

Contributing

See CONTRIBUTING.md for tests, probes, and PR process.

License

See the repository license file if present; otherwise follow the terms ofthe project host.

MCP Server · Populars

MCP Server · New

    drakulavich

    Kesha Voice Kit

    Give your tools a voice — speech to text and back, 25 languages, up to ~19× faster than Whisper. On your machine.

    Community drakulavich
    lobu-ai

    Lobu — Open-source backend for AI teammates

    Open-source control plane and runtime for organisational agents: shared company context, isolated execution, approvals and MCP.

    Community lobu-ai
    minipuft

    Claude Prompts MCP Server

    Wolfflow: Model Context Protocol (MCP) server for reusable prompt templates, multi-step workflow chains, and quality gates. Compose agentic workflows with an operator syntax; export as native skills to Claude Code, Cursor, OpenCode, and Gemini CLI.

    Community minipuft
    docmancer

    Docmancer

    Find out what your coding agents already know. Docmancer indexes the memory, rules, and instructions Claude Code, Codex, Cursor, and Gemini wrote on your machine, then carries the durable parts to every agent. Local-first, MIT.

    Community docmancer
    lineai-intelligence

    codelogic-mcp-server

    An MCP Server to utilize Codelogic's rich software dependency data in your AI programming assistant.