gmat-mcp-server: Instructions file for Claude Code

CLAUDE.md

gmat-mcp-server CLAUDE.md is an instructions file for Claude Code from ginomoretta-creator/gmat-mcp-server. It costs 1,004 tokens per session, scanned A, original, ISC.

Project instructions for a GMAT documentation server that searches technical documentation using meaning-based text search.

In plain words
What is it for?
They help develop the server that downloads, parses, divides, embeds, caches, and searches GMAT documentation.
Why use it?
They give the coding agent a shared understanding of the project's architecture, tools, dependencies, and data pipeline.

Instructions file for Claude Code

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

This is ginomoretta-creator/gmat-mcp-server's own configuration. It tells Claude Code how to work on gmat-mcp-server 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 gmat-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ginomoretta-creator/gmat-mcp-server. 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/ginomoretta-creator/gmat-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ginomoretta-creator/gmat-mcp-server

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 gmat-mcp-server CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ginomoretta-creator/gmat-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/ginomoretta-creator/gmat-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,004 This file is loaded in full into every session.
When invoked 1,004 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 $0.01004 $0.01004
Opus 5 $0.00502 $0.00502
Sonnet 5 $0.00201 $0.00201
Haiku 4.5 $0.00100 $0.00100

Measured 9d ago against content hash ec712aa3fc1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

gmat-mcp-server 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 9d 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 · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 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.

Project Overview

This is a GMAT Documentation MCP (Model Context Protocol) Server that provides semantic search capabilities over GMAT documentation. The server scrapes, parses, chunks, and embeds GMAT documentation content to enable AI assistants to access comprehensive GMAT information through vector search.

Architecture

The project follows a modular architecture with the following phases:

Phase 1: Setup and Dependencies

  • TypeScript-based Node.js project using @modelcontextprotocol/sdk and zod
  • Uses pnpm as package manager (version 10.10.0)
  • Core dependencies for scraping (axios, cheerio), embeddings (openai), and vector search

Phase 2: Data Ingestion Pipeline

  • Scraping: src/utils/scraper.ts - Fetches HTML from GMAT documentation site
  • Parsing: src/utils/parser.ts - Converts HTML to structured chunks using Cheerio, chunks by headings
  • Embedding: src/utils/embedder.ts - Generates embeddings using OpenAI's text-embedding-3-small model
  • Caching: src/utils/cache.ts - Persists embedded chunks to filesystem for performance

Phase 3: MCP Server

  • Search Engine: src/utils/search.ts - In-memory cosine similarity search over embeddings
  • Local Embedder: src/utils/localEmbedder.ts - Query/corpus embeddings via transformers.js (all-MiniLM-L6-v2, 384d); no API key needed at runtime. src/reembedLocal.ts migrates an OpenAI-embedded corpus to local embeddings (npm run reembed).
  • GMAT Tools: src/utils/gmat.ts - runGmat (async headless execution + outcome classification), getGmatIdioms, listGmatSamples, getGmatSample
  • Server: src/index.ts - Main MCP server that loads cached data and handles protocol requests

Common Commands

# Setup (install dependencies)
pnpm install

# Build TypeScript
pnpm run build  # Will need to add to package.json

# Development mode
pnpm run dev    # Will need to add to package.json

# One-time data ingestion (run before starting server)
pnpm run setup  # Will need to add to package.json

# Start MCP server
pnpm start      # Will need to add to package.json

# Tests
pnpm test       # Will need to add to package.json

Read the full file on GitHub · 91 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. 9d ago First seen · 91 lines · 1,004 tokens per session scan A ec712aa3fc1f

Subscribe to this mod's changes

gmat-mcp-server CLAUDE.md is an instructions file published in the GitHub repository ginomoretta-creator/gmat-mcp-server (2 stars, last pushed 3mo ago), licensed ISC. It adds 1,004 tokens to every session, about $0.0050 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

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 · 7,296 tokens

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 · 5,153 tokens

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 · 6,785 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 4,469 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens