What is codex-mcp-server AGENTS.md?

Project-specific instructions for AI coding assistants working on a TypeScript server that exposes tools and calls the Codex command-line program. They describe the source folders, build and documentation commands, and coding conventions.

Use them when adding or changing server tools, utilities, shared constants, documentation, TypeScript builds, or the server's development and lint commands.

They clarify where new tools belong, how they must be registered, and how to build, check, test, and document the server.

How cexll/codex-mcp-server configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to cexll/codex-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/cexll/codex-mcp-server/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/cexll/codex-mcp-server

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/cexll/codex-mcp-server/agents-md/github.svg)](https://agentmods.dev/instructions/cexll/codex-mcp-server/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/cexll/codex-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/cexll/codex-mcp-server/agents-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/cexll/codex-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/cexll/codex-mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 753 This file is loaded in full into every session.

When invoked 753 The same file — it is already loaded in full.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.00753	$0.00753
Opus 5.5	$0.00301	$0.00301
Sonnet 5.5	$0.00151	$0.00151
Haiku 4.5	$0.00075	$0.00075

Measured 2mo ago against content hash a76a1f7f20c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codex-mcp-server AGENTS.md scanned grade A with 0 findings 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

codex-mcp-server AGENTS.md — 100% identical, 0 lines differ

AGENTS.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Structure & Module Organization

src/ TypeScript sources (ESM):
- index.ts MCP entrypoint (stdio server)
- tools/ MCP tools (*.tool.ts), registry.ts, index.ts (registration)
- utils/ execution, logging, parsing helpers
- constants.ts shared types/strings
dist/ compiled output (generated by tsc).
docs/ VitePress docs.
scripts/ maintenance utilities (e.g., wiki deploy).

Example: add a tool under src/tools/my-feature.tool.ts, then register it in src/tools/index.ts by pushing to toolRegistry.

Build, Test, and Development Commands

npm run build — compile TypeScript to dist/.
npm start — run server from dist/.
npm run dev — compile once then run (no watch).
npm run lint — type-check only (tsc --noEmit).
Docs: npm run docs:dev|docs:build|docs:preview — develop/build/preview VitePress site.

Requirements: Node >=16. The server shells out to the codex CLI; ensure it's installed and authenticated in your environment.

Coding Style & Naming Conventions

Language: TypeScript (ESM, Node16 resolution). Imports use .js extensions in src/ to match ESM output.
Indentation: 2 spaces; prefer single quotes in strings except where template literals or readability favors otherwise.
Filenames: kebab-case. Tools end with .tool.ts (e.g., fetch-chunk.tool.ts).
Types: keep zod schemas colocated with tools; export a UnifiedTool and register it.

Testing Guidelines

Currently no automated tests (npm test is a stub). If adding tests, place them alongside sources (e.g., src/**/__tests__) and mirror filenames.
Aim for unit coverage on parsing/execution utilities in src/utils/ and schema validation.

Commit & Pull Request Guidelines

Commits: concise, imperative subject (e.g., feat: add brainstorm tool, fix(utils): handle quota errors).
PRs: include a clear description, linked issues, reproduction steps, and sample CLI output (stdout/stderr) when relevant.
Keep changes scoped; update docs in docs/ or README.md when behavior/CLI changes.

Read the full file on GitHub · 63 lines

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.

2mo ago First seen · 63 lines · 753 tokens per session scan A a76a1f7f20c8

Subscribe to this mod's changes

codex-mcp-server AGENTS.md is an instructions file published in the GitHub repository cexll/codex-mcp-server (176 stars, last pushed 5mo ago), licensed MIT. It adds 753 tokens to every session, about $0.0030 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

codex-mcp-server AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
codex-mcp-server AGENTS.mdcexll/codex-mcp-server	Instructions file	176	5mo ago	MIT	A	753	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

codex-mcp-server: Instructions file for Codex