gen-mcp: Instructions file for Codex

AGENTS.md

gen-mcp AGENTS.md is an instructions file for Codex, OpenCode from genmcp/gen-mcp. It costs 593 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for GenMCP, a Go tool that creates MCP servers—services that let AI agents call existing APIs or command-line programs.

In plain words
What is it for?
Use it when working on MCP file formats, server generation, API or command conversion, authentication, containers, or the GenMCP command-line tool.
Why use it?
It maps the project structure and development practices, so changes are made in the right package and tested consistently.

Instructions file for CodexOpenCode

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

This is genmcp/gen-mcp's own configuration. It tells Codex and OpenCode how to work on gen-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 gen-mcp configures →

Reuse

Borrowing it

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

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/genmcp/gen-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/genmcp/gen-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 593 This file is loaded in full into every session.
When invoked 593 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 $0.00593 $0.00593
Opus 5.5 $0.00237 $0.00237
Sonnet 5.5 $0.00119 $0.00119
Haiku 4.5 $0.00059 $0.00059

Measured 2mo ago against content hash 8784fcbc1be6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gen-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 · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GenMCP Dev Guidance

GenMCP provides a declarative way to create MCP servers around existing systems The declarative file formats are described in ./docs/mcpfile.md (tool definitions) and ./docs/mcpserver.md (server config) Some examples can be found in ./examples/

Repository Layout

  • ./pkg/builder: builder to create container images from an MCP file that will contain the mcp server
  • ./pkg/cli: cli commands and utilities for the genmcp cli
  • ./pkg/converter: packages to automatically convert different types of applications into an MCP file. Currently, there are subpackages for OpenAPI specs and cli conversion with an agent
  • ./pkg/invocation/: core invocation interfaces and utilities. Subpackages for specific invocation types (http, cli)
  • ./pkg/mcpfile/: core types for the mcp file
  • ./pkg/mcpserver/: core mcp server implementation
  • ./pkg/oauth/: OAuth helpers, primarily to be used in ./pkg/mcpserver
  • ./pkg/observability/: observability packages to be used throughout
  • ./cmd/genmcp/: the entry point for the genmcp CLI
  • ./cmd/genmcp-server/: the entry point for the genmcp server binary (to be used in containers)
  • ./examples/: various examples of how to use genmcp
  • ./docs/: docs around the mcp file spec
  • ./specs/: generated json schema specs for the mcp file format
  • ./test/: integration tests for the project

Dev commands

There are more makefile commands than those listed here, but these are the only ones you need to worry about while developing genmcp

  • make build: build everything - in general, this is how to build the project
  • make update-codegen: this will update the codegen for the json schemas. Call this whenever you make changes to the core types
  • make test: this will correctly re-build required binaries and run all the tests

Coding Guidelines

  • When adding logs, check whether you are using the server-only logger (embedded in the MCPServer type, and accessed from invocation contexts with logging.BaseFromContext(ctx)) or the server and client logger. Make sure that any logs with sensitive info use the server-only logger
  • When writing unit tests, follow the table test convention used throughout the codebase

Read the full file on GitHub · 40 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 · 40 lines · 593 tokens per session scan A 8784fcbc1be6

Subscribe to this mod's changes

gen-mcp AGENTS.md is an instructions file published in the GitHub repository genmcp/gen-mcp (46 stars, last pushed 4d ago), licensed Apache-2.0. It adds 593 tokens to every session, about $0.0024 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.

Related

gen-mcp AGENTS.md compared with instructions from other repositories

gen-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
gen-mcp AGENTS.mdgenmcp/gen-mcpInstructions file464d agoApache-2.0A593Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
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