agentmods.dev

setup-mcp-codex

setup-mcp-codex is a command for Claude Code from ContoriumLabs/contorium. It costs 22 tokens per session (323 once invoked), scanned B, original, MIT.

A setup command for building Contorium and connecting its memory tools to Codex. Codex is OpenAI's coding agent, and MCP is a standard way to provide it with external tools.

In plain words
What is it for?
Use it to install the Codex plugin or add the local MCP server, then access tools for storing, searching, and retrieving workspace memory and context.
Why use it?
It avoids manual configuration and documents a local setup that prevents unwanted console windows on Windows.

Command for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads ~/.codex paths; mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node scripts/setup-codex-mcp-local.mjs.

Part of the contorium plugin — 1 skill, 5 commands, 1 MCP server shipped together

not rated 7repo 3mo ago B scan 22 tokens original MIT

Good fit Use it to install the Codex plugin or add the local MCP server, then access tools for storing, searching, and retrieving workspace memory and context.

Compare 6 commands from other repositories ↓
View source ↗ ContoriumLabs/contorium contorium.dev
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/ContoriumLabs/contorium
agentmods
npx agentmods add commands/contoriumlabs/contorium/setup-mcp-codex

Made for: Claude Code.

Or install contorium, the plugin that ships this one along with the rest of its 1 skill, 5 commands, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for setup-mcp-codex

README.md
[![agentmods](https://agentmods.dev/badge/commands/contoriumlabs/contorium/setup-mcp-codex/github.svg)](https://agentmods.dev/commands/contoriumlabs/contorium/setup-mcp-codex)
Your own site
<a href="https://agentmods.dev/commands/contoriumlabs/contorium/setup-mcp-codex"><img src="https://agentmods.dev/badge/commands/contoriumlabs/contorium/setup-mcp-codex/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for setup-mcp-codex

Your own site · 80×15
<a href="https://agentmods.dev/commands/contoriumlabs/contorium/setup-mcp-codex"><img src="https://agentmods.dev/badge/commands/contoriumlabs/contorium/setup-mcp-codex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 323 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.00323
Opus 5.5 $0.00009 $0.00129
Sonnet 5.5 $0.00004 $0.00065
Haiku 4.5 $0.00002 $0.00032

Measured 2mo ago against content hash a7891947fce4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

setup-mcp-codex scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

This patches `~/.codex/config.toml` to use `node E:/sessionrecall/packages/mcp/bin/contorium-mcp.js` instead of `npx @contorium/mcp` (npx opens visible console windows).
commands/setup-mcp-codex.md · 23 lines

What it actually says

Setup Contorium for Codex

  1. From the repository root: npm run build:mcp (or npm run compile).

  2. Plugin (recommended): install this repo as a Codex plugin (manifest at .codex-plugin/plugin.json, MCP at .mcp.json).

  3. MCP only (local dev — recommended on Windows):

    node scripts/setup-codex-mcp-local.mjs

    This patches ~/.codex/config.toml to use node E:/sessionrecall/packages/mcp/bin/contorium-mcp.js instead of npx @contorium/mcp (npx opens visible console windows).

    Or manually: codex mcp add contorium -- node E:/sessionrecall/packages/mcp/bin/contorium-mcp.js

  4. Do not use npx @contorium/mcp on Windows — it spawns npm exec contorium bootstrap flash windows.

  5. Keep the Contorium VS Code/Cursor extension for sidebar UI and .contora/state.json; Codex MCP tools complement the extension.

Tools: store_memory, search_memory, get_memory, get_workspace_context.

See docs/MCP.md and OpenAI Codex plugins.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 23 lines · 22 tokens per session scan B a7891947fce4

Subscribe to this mod's changes

setup-mcp-codex is a command published in the GitHub repository ContoriumLabs/contorium (7 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 323 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agentsClaude Codeai-agentscodex-clicontext-engineeringgemini-climcp-server
Related

setup-mcp-codex compared with commands from other repositories

setup-mcp-codex next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
setup-mcp-codexContoriumLabs/contoriumCommand73mo agoMITB22Claude Code
rb-askstudy8677/repobrainCommand1.4k14d agoMITA33Claude Code
rb-refreshstudy8677/repobrainCommand1.4k14d agoMITA25Claude Code
session-stopsageox/oxCommand67yesterdayMITA0Claude Code
statussageox/oxCommand67yesterdayMITA0Claude Code
sync-allathola/skrillsCommand696d agoMITA25Claude Code
sync-from-copilotathola/skrillsCommand696d agoMITA19Claude Code