IP-MCP CLAUDE.md

IP-MCP CLAUDE.md is an instructions file for Claude Code from AI-AlexBaum/IP-MCP. It costs 1,734 tokens per session, scanned A, original, MIT.

Repository instructions for an MCP server that researches trademarks and companies using public registers. MCP is a way for an AI agent to call external tools.

In plain words
What is it for?
Use them when developing or checking the server, running its tests, inspecting syntax, sending tool requests, or adding a tool.
Why use it?
They give an agent the commands, architecture, test checks, and credential rules needed to work on the server safely.

Instructions file for Claude Code

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

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/ai-alexbaum/ip-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/AI-AlexBaum/IP-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 IP-MCP CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ai-alexbaum/ip-mcp/claude-md.svg)](https://agentmods.dev/instructions/ai-alexbaum/ip-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ai-alexbaum/ip-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ai-alexbaum/ip-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,734 This file is loaded in full into every session.
When invoked 1,734 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01734 $0.01734
Opus 5 $0.00867 $0.00867
Sonnet 5 $0.00347 $0.00347
Haiku 4.5 $0.00173 $0.00173

Measured 5d ago against content hash 42c9226fb2c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

IP-MCP 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 5d 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.

CLAUDE.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 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 is

An MCP server for trademark and company research over public registers. One file, zero dependencies, Node 18+, ESM. It speaks MCP over stdio with a hand-rolled JSON-RPC loop — there is no SDK, no build step and no bundler.

Distribution is npx -y github:AI-AlexBaum/IP-MCP, straight from the repo. Nothing is published to npm, so package.json's bin and files must stay correct or the install path silently breaks.

Commands

npm run smoke              # the entire test suite (24 checks, hits live registers)
node --check src/index.js  # syntax gate
node src/index.js          # speaks MCP on stdin/stdout

To run a single check, pipe one JSON-RPC line in — this is the fastest way to iterate on a tool:

printf '%s\n' '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"tm_clearance","arguments":{"name":"Northwind"}}}' \
  | node src/index.js

The paid tools need credentials in the environment, never in the repo:

COMPANYINFO_USERNAME=… COMPANYINFO_PASSWORD=… node src/index.js

The smoke test calls live third-party APIs. A failure can mean upstream drift rather than a regression — check the endpoint by hand before assuming the code broke. The four paid nl_company_* tools are deliberately not in the suite: each run would cost money and return real company data. Verify those by hand when you touch them.

Architecture

src/index.js is layered top to bottom:

  1. ConstantsOFFICES (register codes), LIVE (which statuses count as a live right), VIES_MS (VAT member states).
  2. http() — every outbound call goes through it. Three retries with backoff, 90s timeout, throws on non-2xx. It never converts a failure into an empty result.
  3. Source adapters, one group per data source: TMview + EUIPO copla (trademarks), GLEIF + VIES (companies), EU_REGISTERS (sixteen national registers), and the Company.info SOAP layer (paid, Dutch Handelsregister).
  4. TOOLS — JSON schemas — and HANDLERS — name → function.
  5. stdio loop — line-buffered reader plus dispatch(), which tracks in-flight requests so a client closing stdin mid-call does not drop pending replies.

Read the full file on GitHub · 140 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. 5d ago First seen · 140 lines · 1,734 tokens per session scan A 42c9226fb2c6

Subscribe to this mod's changes

IP-MCP CLAUDE.md is an instructions file published in the GitHub repository AI-AlexBaum/IP-MCP (0 stars, last pushed 8d ago), licensed MIT. It adds 1,734 tokens to every session, about $0.0087 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 2026-08-31.

Related

Other instructions, from other repositories