mcp-composer: Instructions file for Codex

AGENTS.md

mcp-composer AGENTS.md is an instructions file for Codex, OpenCode from IBM/mcp-composer. It costs 249 tokens per session, scanned A, original, Apache-2.0.

A repository instruction guide for contributors and coding agents working on IBM/mcp-composer. It describes where code and tests live, which checks to run, and which security rules not to weaken.

In plain words
What is it for?
It is for making scoped changes, running Python tests and code checks, and avoiding private deployment details or removed product adapters.
Why use it?
It reduces accidental out-of-scope edits and makes the project's contribution requirements clear. It also guards authentication, allowlists, and network-binding behavior.

Instructions file for CodexOpenCode ✓ vendor

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

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

About the project

MCP Composer is a FastMCP server that combines tools from multiple Model Context Protocol servers behind one endpoint. It is for exposing member servers that use HTTP, SSE, stdio, OpenAPI, or GraphQL through a single configured tool surface. The catalogue instruction supports working with this composer.

IBM/mcp-composer · 22 stars · on GitHub · ibm.github.io

Reuse

Borrowing it

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

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-composer AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ibm/mcp-composer/agents-md"><img src="https://agentmods.dev/badge/instructions/ibm/mcp-composer/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 249 This file is loaded in full into every session.
When invoked 249 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 $0.00249 $0.00249
Opus 5.5 $0.00100 $0.00100
Sonnet 5.5 $0.00050 $0.00050
Haiku 4.5 $0.00025 $0.00025

Measured 21d ago against content hash d3e9a3366312, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-composer 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 21d 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 · 30 lines

What it actually says

Agent notes

Read CONTRIBUTING.md before changing this repository. The same rules apply to human and agent authors: a short problem statement, a reproduction, a scoped diff, and tests.

Layout

  • Package: modules/mcp_composer (src/mcp_composer)
  • Unit tests: modules/mcp_composer/tests/unit
  • Docs: docs/
  • Root Makefile targets expect module=mcp_composer

Required checks

From modules/mcp_composer:

uv sync --group dev
uv run pytest tests/unit -q
uv run ruff check .
uv run black --check .

Do not treat a green test run as permission to change an intentional security contract. Stdio member servers require MCP_COMPOSER_STDIO_ALLOWLIST. Non-loopback HTTP binds require authentication.

Out of scope for drive-by edits

  • Internal deployment hostnames, registries, and private GitHub links do not belong in public docs.
  • Do not reintroduce removed product-specific adapters or examples.
  • Do not weaken auth, allowlist, or default-bind checks to make a test pass.
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. 21d ago First seen · 30 lines · 249 tokens per session scan A d3e9a3366312

Subscribe to this mod's changes

mcp-composer AGENTS.md is an instructions file published in the GitHub repository IBM/mcp-composer (22 stars, last pushed today), licensed Apache-2.0. It adds 249 tokens to every session, about $0.0010 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 2026-10-09.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,750 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens