What is graphql2mcp CLAUDE.md?

Project instructions for graphql2mcp, a monorepo that contains multiple related packages managed with pnpm workspaces. The project converts GraphQL schemas and endpoints into MCP servers.

It is for working on the conversion engine, proxy server, command-line tools, and individual packages, including their unit and integration tests.

It gives an agent the project's structure and standard commands for building, testing, linting, formatting, and checking types.

How KKonstantinov/graphql2mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to KKonstantinov/graphql2mcp. 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/KKonstantinov/graphql2mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/KKonstantinov/graphql2mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/kkonstantinov/graphql2mcp/claude-md/github.svg)](https://agentmods.dev/instructions/kkonstantinov/graphql2mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/kkonstantinov/graphql2mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kkonstantinov/graphql2mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/kkonstantinov/graphql2mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/kkonstantinov/graphql2mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 528 This file is loaded in full into every session.

When invoked 528 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.

Model	Per session	Once invoked
Fable 5.1	$0.00528	$0.00528
Opus 5.5	$0.00211	$0.00211
Sonnet 5.5	$0.00106	$0.00106
Haiku 4.5	$0.00053	$0.00053

Measured 2mo ago against content hash 3fc56def20be, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

graphql2mcp 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 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.

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 · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 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

graphql2mcp converts GraphQL schemas and endpoints into MCP (Model Context Protocol) servers. Monorepo with pnpm workspaces.

Common Commands

pnpm build                # Build all packages (tsdown)
pnpm test                 # Run all unit tests (vitest)
pnpm test:watch           # Watch mode
pnpm test:integration     # Build + run integration tests
pnpm lint                 # ESLint (includes Prettier checks)
pnpm lint:fix             # ESLint with auto-fix
pnpm format               # Prettier --write
pnpm typecheck            # TypeScript type checking

Run for a specific package:

pnpm --filter graphql2mcp test
pnpm --filter @graphql2mcp/core test
pnpm --filter @graphql2mcp/lib test

Run a single test file:

pnpm vitest run packages/core/test/unit/example.test.ts

Architecture

Package Structure

packages/core/ — Shared conversion engine (@graphql2mcp/core). GraphQL schema parsing → MCP tool definitions
packages/proxy/ — Standalone proxy (graphql2mcp). CLI + server that proxies a GraphQL endpoint as an MCP server
packages/lib/ — Library (@graphql2mcp/lib). For integrating into existing TypeScript MCP servers

Both proxy and lib depend on core via workspace:*.

Code Conventions

ESM only — all imports use .js extension (TypeScript ESM convention)
No as any — use proper type guards
Prettier: 140 char width, 4-space indent, single quotes, no trailing commas, arrowParens: "avoid"
Enforce import type for type-only imports

Testing Conventions

Test through the public API when possible
Use toContain for flexible output assertions (avoids whitespace brittleness)
Use toBe only for exact formatting tests
Unit tests in test/unit/, integration tests in test/integration/

After Making Changes

Always run lint, typecheck, and tests before considering a change complete:

Read the full file on GitHub · 67 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.

2mo ago First seen · 67 lines · 528 tokens per session scan A 3fc56def20be

Subscribe to this mod's changes

graphql2mcp CLAUDE.md is an instructions file published in the GitHub repository KKonstantinov/graphql2mcp (1 stars, last pushed 24d ago), licensed MIT. It adds 528 tokens to every session, about $0.0021 per session on Opus 5.5. 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.

ai-agents cli graphql llm-tools mcp model-context-protocol

graphql2mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
graphql2mcp CLAUDE.mdKKonstantinov/graphql2mcp	Instructions file	1	24d ago	MIT	A	528	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

graphql2mcp: Instructions file for Claude Code