mcp: Instructions file for Codex

AGENTS.md

mcp AGENTS.md is an instructions file for Codex, OpenCode from pexcard/mcp. It costs 1,629 tokens per session, scanned A, original, MIT.

Project instructions for coding agents working on a TypeScript server that exposes read-only tools for the PEX Card External API. They describe the project's purpose, commands, structure, and design limits.

In plain words
What is it for?
Understanding how to build and run the server, locating its TypeScript files, following its logging and API-client conventions, and adding or reviewing tools consistently.
Why use it?
They give an agent the local rules it needs before changing code, including that the API access is read-only and that the project has no tests yet. This helps prevent unsupported build steps or unsafe changes.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is pexcard/mcp's own configuration. It tells Codex and OpenCode how to work on mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to pexcard/mcp. 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/pexcard/mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/pexcard/mcp

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.

agentmods badge for mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pexcard/mcp/agents-md/github.svg)](https://agentmods.dev/instructions/pexcard/mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/pexcard/mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/pexcard/mcp/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.

agentmods 80×15 button for mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/pexcard/mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/pexcard/mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,629 This file is loaded in full into every session.
When invoked 1,629 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01629 $0.01629
Opus 5.5 $0.00652 $0.00652
Sonnet 5.5 $0.00326 $0.00326
Haiku 4.5 $0.00163 $0.00163

Measured 2mo ago against content hash 74d07c813694, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp 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.

AGENTS.md · 165 lines

How it starts

The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Instructions for AI coding agents working on this project.

Project Overview

A Model Context Protocol (MCP) server in TypeScript that wraps the PEX Card External API as 72 read-only tools. Runs as a stdio-based process using @modelcontextprotocol/sdk. Read-only by design — only GET endpoints are exposed.

Build & Run

npm ci                # install dependencies
npm run build         # compile TypeScript (tsc → dist/)
npm run dev           # run in development mode (tsx, no build needed)
npm start             # run compiled output (dist/index.js)
npm audit --audit-level=high  # check for vulnerabilities

There are no tests yet. Do not add a npm test step to scripts without being asked.

Project Structure

src/
├── index.ts              # Entry point: creates server, registers tools, connects transport
├── pex-client.ts         # HTTP client (GET-only, retry, error handling)
├── logger.ts             # JSON structured logger (writes to stderr only)
├── types.ts              # Shared type: ToolRegistrar
└── tools/
    ├── index.ts           # Aggregator — calls all register() functions
    ├── utils.ts           # toolResponse, toolError, paginateArray, paginateNestedArray, readOnlyAnnotations
    ├── business.ts        # 12 tools
    ├── card.ts            # 7 tools
    ├── transactions.ts    # 10 tools
    ├── details.ts         # 10 tools
    ├── spending-ruleset.ts # 7 tools
    ├── bill.ts            # 4 tools
    ├── vendor.ts          # 2 tools
    ├── vendor-card.ts     # 1 tool
    ├── payment.ts         # 3 tools
    ├── credit.ts          # 4 tools
    ├── group.ts           # 2 tools
    ├── token.ts           # 3 tools
    ├── token-provisioning.ts # 3 tools
    ├── callback.ts        # 3 tools
    └── partner.ts         # 1 tool

Architecture

Entry point (src/index.ts): Creates McpServer, instantiates PexClient, calls registerAllTools(), and connects via StdioServerTransport. All logging goes to stderr to keep stdout clean for MCP protocol.

Read the full file on GitHub · 165 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.

  1. 2mo ago First seen · 165 lines · 1,629 tokens per session scan A 74d07c813694

Subscribe to this mod's changes

mcp AGENTS.md is an instructions file published in the GitHub repository pexcard/mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 1,629 tokens to every session, about $0.0065 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 2026-08-31.

Related

mcp AGENTS.md compared with instructions from other repositories

mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp AGENTS.mdpexcard/mcpInstructions file14mo agoMITA1,629Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,649GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot