mcp: Instructions file for Claude Code

CLAUDE.md

mcp CLAUDE.md is an instructions file for Claude Code from oopsyz/mcp. It costs 523 tokens per session, scanned B, a copy of mcp AGENTS.md, MIT.

A project instruction file for the oopsyz/mcp system. It points agents to the required guidance files and documents how to discover, ask about, and run TMF620 catalog commands through a local HTTP interface.

In plain words
What is it for?
Use it when working in the oopsyz/mcp project, especially when interacting with its TMF620 catalog-management commands.
Why use it?
It gives agents a defined starting point and command interface instead of leaving them to guess how this system should be used.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is oopsyz/mcp's own configuration. It tells Claude Code 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 →

View source ↗ oopsyz/mcp
Reuse

Borrowing it

Nothing to install: this file belongs to oopsyz/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/oopsyz/mcp/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/oopsyz/mcp

Made for: Claude Code.

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 CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/oopsyz/mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/oopsyz/mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 523 This file is loaded in full into every session.
When invoked 523 The same file — it is already loaded in full.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 89% copy Near-identical to another mod 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 $0.00523 $0.00523
Opus 5.5 $0.00209 $0.00209
Sonnet 5.5 $0.00105 $0.00105
Haiku 4.5 $0.00052 $0.00052

Measured 2mo ago against content hash 02d1c9895b96, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

mcp CLAUDE.md scanned grade B with 2 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

- `curl -s -X POST http://localhost:7701/cli/tmf620/catalogmgt -H "Content-Type: application/json" -d '{"command":"help","args":{"command":"catalog list"}}'`

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

For TMF620 command discovery and invocation, use the bash tool with `curl` against the HTTP CLI API. This is the preferred interface for Claude agents.
Origin

This is a copy

89% identical to mcp AGENTS.md — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 47 lines

What it actually says

CLAUDE

Role: da Bootstrap: Read AGENTS.md first. Instruction: Then read DOMAIN.md (mandatory entrypoint for this level). Guardrail: AGENTS.md and DOMAIN.md remain the canonical contract files. Keep mutable operational detail in linked canonical artifacts, not in CLAUDE.md.

Claude Guidance

Preferred Interface

For TMF620 command discovery and invocation, use the bash tool with curl against the HTTP CLI API. This is the preferred interface for Claude agents.

  • Discovery: GET http://localhost:7701/cli/tmf620/catalogmgt
  • Per-command help: POST http://localhost:7701/cli/tmf620/catalogmgt with {"command":"help","args":{"command":"<command path>"}}
  • Invoke: POST http://localhost:7701/cli/tmf620/catalogmgt with {"command":"<command path>","args":{...}}
  • Stream: add "stream": true to the same POST body

Preferred shell pattern:

  • curl -s http://localhost:7701/cli/tmf620/catalogmgt
  • curl -s -X POST http://localhost:7701/cli/tmf620/catalogmgt -H "Content-Type: application/json" -d '{"command":"help","args":{"command":"catalog list"}}'
  • curl -s -X POST http://localhost:7701/cli/tmf620/catalogmgt -H "Content-Type: application/json" -d '{"command":"catalog list","args":{"limit":1}}'

Source of Truth

The shared command layer lives in tmf620/commands.py.

  • tmf620/server.py exposes the HTTP CLI API and MCP server

When changing command names, arguments, discovery output, or invocation behavior, update tmf620/commands.py first.

Local URLs

  • Mock TMF620 API: http://localhost:8801/tmf-api/productCatalogManagement/v5
  • MCP server and HTTP CLI API: http://localhost:7701
  • HTTP CLI API endpoint: http://localhost:7701/cli/tmf620/catalogmgt

Validation Order

When validating command behavior, prefer this order:

  1. GET /cli/tmf620/catalogmgt
  2. POST /cli/tmf620/catalogmgt with help
  3. POST /cli/tmf620/catalogmgt invoke
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 · 47 lines · 523 tokens per session scan B 02d1c9895b96

Subscribe to this mod's changes

mcp CLAUDE.md is an instructions file published in the GitHub repository oopsyz/mcp (3 stars, last pushed 4mo ago), licensed MIT. It adds 523 tokens to every session, about $0.0021 per session on Opus 5.5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). It is 89% identical to mcp AGENTS.md, differing in 11 lines, and is treated as a copy.

Related

mcp CLAUDE.md compared with instructions from other repositories

mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp CLAUDE.mdoopsyz/mcpInstructions file34mo agoMITB523Claude Code
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 ai-customization.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA1,907GitHub Copilot