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.
npx agentmods add instructions/magebitcom/magento2-mcp-module/claude-mdgit clone --depth 1 https://github.com/magebitcom/magento2-mcp-moduleWrote 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.
[](https://agentmods.dev/instructions/magebitcom/magento2-mcp-module/claude-md)<a href="https://agentmods.dev/instructions/magebitcom/magento2-mcp-module/claude-md"><img src="https://agentmods.dev/badge/instructions/magebitcom/magento2-mcp-module/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.04170 | $0.04170 |
| Opus 5 | $0.02085 | $0.02085 |
| Sonnet 5 | $0.00834 | $0.00834 |
| Haiku 4.5 | $0.00417 | $0.00417 |
Grade A, and why
magento2-mcp-module CLAUDE.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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What this module is
Magento 2 implementation of the Model Context Protocol (MCP, spec version 2025-06-18). Ships the transport, auth, ACL, audit, and tool registry — a single POST /mcp endpoint that speaks JSON-RPC 2.0 over HTTP with bearer auth. Domain tools live in satellite modules (Magebit_McpOrderTools, Magebit_McpCatalogTools, Magebit_McpCustomerTools, Magebit_McpCmsTools, Magebit_McpMarketingTools, Magebit_McpTaxTools, Magebit_McpReportTools, Magebit_McpGoogleAnalyticsTools, and Magebit_McpDbTools — the last one ships raw read-only SQL, is off by default, and is the canonical ContextualAclAwareInterface consumer); this repo ships its own set of 19 core system.* tools — store/config info, cache and indexer control, admin notifications, connection identity (system.whoami), scheduled-job diagnostics (system.cron.status), read-only log access (system.log.list / system.log.tail / system.log.grep), and allowlisted config writing (system.config.set).
The repo is checked out as a Magento module at app/code/Magebit/Mcp. The Magento root is /var/www/demo — Composer, bin/magento, and vendor/bin/* all run from there, not from this directory. Read the root README.md for protocol-level detail and client-onboarding snippets — this file complements it with architecture and workflow notes.
Commands
All commands run from the Magento root (/var/www/demo).
# Enable / rebuild after XML or DI changes
bin/magento module:enable Magebit_Mcp
bin/magento setup:upgrade
bin/magento setup:di:compile
bin/magento cache:flush
# Module-specific CLI
bin/magento magebit:mcp:tools:list # Every registered tool, ACL, write mode
bin/magento magebit:mcp:tools:validate-acl # CI gate: tool ACLs must resolve + names must match regex
bin/magento magebit:mcp:token:create --admin-user=<u> --name='<label>'
bin/magento magebit:mcp:token:{list,revoke,delete}
# Static analysis — PHPStan level 9 on this module
vendor/bin/phpstan analyse app/code/Magebit/Mcp -c app/code/Magebit/Mcp/phpstan.neon
# Unit tests (module-scoped)
vendor/bin/phpunit -c dev/tests/unit/phpunit.xml.dist app/code/Magebit/Mcp/Test/Unit
# Single test class
vendor/bin/phpunit -c dev/tests/unit/phpunit.xml.dist app/code/Magebit/Mcp/Test/Unit/Model/JsonRpc/DispatcherTest.php
# Single method
vendor/bin/phpunit -c dev/tests/unit/phpunit.xml.dist --filter testDispatchMethodNotFound app/code/Magebit/Mcp/Test/Unit/Model/JsonRpc/DispatcherTest.php
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.
- 3d ago First seen · 164 lines · 4,170 tokens per session scan A 143244f7cc8c
magento2-mcp-module CLAUDE.md is an instructions file published in the GitHub repository magebitcom/magento2-mcp-module (19 stars, last pushed 15d ago), licensed MIT. It adds 4,170 tokens to every session, about $0.0209 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.
Other instructions, from other repositories
ebay-mcp AGENTS.md
Instructions for YosefHayim/ebay-mcp, covering agents.md, what this is, instruction sources, validation commands and module map (src/).
mcp-server-amazon CLAUDE.md
Instructions for rigwild/mcp-server-amazon, covering claude.md, development commands, install dependencies (use -d flag for puppeteer), build typescript to javascript and clean mock html files.
rakuten-mcp AGENTS.md
Instructions for mrslbt/rakuten-mcp, covering agents.md — rakuten-mcp, what this project is, quick commands, architecture and two non-negotiable conventions.
mcp-shopline CLAUDE.md
Instructions for asgard-ai-platform/mcp-shopline, covering claude.md, project overview, setup & running, run the mcp server directly (stdio json-rpc 2.0) and or auto-detected via .mcp.json when opened in claude code.
apify-mcp-server CLAUDE.md
Claude Code instructions for apify/apify-mcp-server, a project described as: The Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website using thousands of ready-made scrapers, crawlers, and automation tools available on the Apify Store.
bestprice-mcp GEMINI.md
Gemini CLI instructions for TheBestCo/bestprice-mcp: Use the BestPrice tools when a user wants to find or compare products sold in Greece or understand whether a current price is low.