What is mmcp AGENTS.md?

Repository guidance for mmcp, a command-line tool that keeps MCP server settings in one file and applies them to several coding-agent applications.

Understanding mmcp’s codebase, running its linter, type checker, build, and tests, and following its contribution workflow.

It gives contributors the project structure, development commands, and checks required before committing changes.

mmcp AGENTS.md — Instructions file by koki-develop

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add instructions/koki-develop/mmcp/agents-md

Clone the repo

git clone --depth 1 https://github.com/koki-develop/mmcp

Made for: Codex, OpenCode.

Per session 990 This file is loaded in full into every session.

When invoked 990 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

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	$0.00990	$0.00990
Opus 5	$0.00495	$0.00495
Sonnet 5	$0.00198	$0.00198
Haiku 4.5	$0.00099	$0.00099

Measured 2d ago against content hash 88006d5669e3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mmcp 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 2d 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 · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Project Overview

mmcp is a CLI tool to manage MCP (Model Context Protocol) server definitions in one centralized config (~/.mmcp.json) and apply them to various agent configs (Claude Code, Claude Desktop, Cursor, Codex CLI, Gemini CLI, GitHub Copilot CLI).

Essential Commands

# Development workflow
bun install                 # Install dependencies
bun run lint                # Run Biome linter (read-only)
bun run fmt                 # Format and fix with Biome (writes changes)
bun run typecheck           # TypeScript type checking
bun run build               # Build CLI to dist/index.js
bun test                    # Run all tests
bun test <file>             # Run specific test file

# Pre-commit check (same as CI)
bun run lint && bun run typecheck && bun run build && bun test

Architecture

Agent Adapter Pattern

The core architecture uses an adapter pattern for supporting multiple agents. Each agent has different config formats (JSON, TOML) and locations:

src/lib/agents/adapter.ts: Defines AgentAdapter interface with id, applyConfig(), and configPath() methods
src/lib/agents/registry.ts: Central registry of all agent adapters; use getAgentById() to retrieve adapters
Individual adapters (claude-code.ts, codex-cli.ts, etc.): Implement agent-specific logic:
- JSON-based agents (Claude Code, Claude Desktop, Cursor, Gemini CLI, GitHub Copilot CLI) merge MCP servers into existing JSON configs
- TOML-based agents (Codex CLI) use @shopify/toml-patch to patch TOML content

Adding a new agent:

Create adapter class in src/lib/agents/<agent-name>.ts implementing AgentAdapter
Implement applyConfig() to merge mmcp's Config into agent's config file
Register in src/lib/agents/registry.ts
Update README.md supported agents table

Config Management

src/lib/config.ts: Manages ~/.mmcp.json with Zod schema validation
Config schema: { mode: "merge"|"replace", agents: string[], mcpServers: Record<string, MCPServer> } (mode defaults to merge)
MCPServer schema allows url, command, args, and env (all optional/partial)
Apply mode merge keeps existing agent entries unless overridden by mmcp, while replace rewrites each agent's MCP servers solely from mmcp.

Read the full file on GitHub · 94 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.

2d ago First seen · 94 lines · 990 tokens per session scan A 88006d5669e3

Subscribe to this mod's changes

mmcp AGENTS.md is an instructions file published in the GitHub repository koki-develop/mmcp (40 stars, last pushed 4d ago), licensed MIT. It adds 990 tokens to every session, about $0.0049 per session on Opus 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.

DevOps and cloud Git and workflow Testing

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

buildNext

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 · 6,785 tokens

mmcp AGENTS.md