← Index

Codex Subagent

io.github.parisbs/codex-subagent-mcpv0.4.0AI & LLMs

Delegate coding tasks to the OpenAI Codex CLI, installed separately, with explicit model and effort.

The current version, v0.4.0, was published to the official MCP registry on 2026-09-30. It is distributed as codex-subagent-mcp on npm, filed under AI & LLMs by this index, and declares 7 environment variables. Removals and unreachable sources are measured across every server this index tracks, contract drift across the servers that answer in consecutive snapshots; the index's current counts put this record in context.

In-path gate · all MCP tools

Using Codex Subagent in Claude, Cursor, Gemini CLI, Cline, or Zed?

MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).

Install the mcpindex gate (one command)

Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less

uv tool install mcpindex-gate && mcpindex-config-wire
Auditable install path →Watch it hold a drift →
Trust verdict · v1 advisory · method
NOT YET SCREENEDno verdict on file

Verdict not yet evaluated for this tool. The semantic screen takes adversarial cases first; coverage rolls out as the corpus expands (15/150 labels to graduation). The deterministic conformance probe is built but has not yet run on the public corpus, so a recorded verdict here is REVIEW or UNVERIFIED, never a clearing ALLOW. Until a verdict is recorded, an agent should treat this tool as not-yet-cleared and fall back to its own checks. Method: the eval, four-state verdict, honest limits.

Own this server? Screen its description →

That verdict was true at screening time (snapshot 2026-10-01).

Contracts can change after screening, with no version bump. The gate pins Codex Subagent’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.

See your first HOLD in 2 minutes →

Related: how to trust an MCP server · screen before install · silent contract drift

Environment variables
CODEX_SUBAGENT_DEFAULT_MODEL

Model used when a call names none; without it the server asks which model to use.

CODEX_SUBAGENT_DEFAULT_EFFORT

Reasoning effort used when a call specifies none.

CODEX_SUBAGENT_ALLOWED_MODELS

Comma-separated allow-list of model slugs; anything else is refused.

CODEX_SUBAGENT_DEFAULT_SANDBOX

Sandbox used when a call specifies none. Defaults to read-only and cannot exceed the ceiling.

CODEX_SUBAGENT_MAX_SANDBOX

Ceiling on what a delegation may do. Defaults to workspace-write; danger-full-access must be set explicitly.

CODEX_SUBAGENT_MAX_EFFORT

Ceiling on reasoning effort.

CODEX_BIN

Path to the Codex executable, if it is not codex on PATH. On Windows it must be codex.exe, not a .cmd shim.

MCP quality score · maturity, not trust · methodology
freshness
25
completeness
20
installability
25
documentation
15
stability
5
Alternatives in AI & LLMs
HeatPulse
cc.heatpulse/heatpulse

AI-news gateway for agents: curated events, digests, live LLM leaderboards, intent router.

Zarla Website Builder
com.zarla/website-builder

Build, edit and publish websites from Claude, ChatGPT, Cursor and Gemini. No code — Zarla hosts it.

Perplexity API Platform (moved to ai.perplexity/mcp-server)
io.github.perplexityai/mcp-server

Real-time web search, reasoning, and research through Perplexity's API