What is mcp-suite CLAUDE.md?

Repository-specific instructions for Claude Code, an AI coding assistant, in an npm workspaces monorepo. They explain the project, commands, naming rules, build checks, and a basic test procedure.

Building all or one TypeScript package, cleaning build output, checking CI requirements, and manually testing MCP servers with JSON-RPC.

They give the assistant the project context and required checks, reducing guesswork and preventing changes that break the repository's conventions.

How Abhishekkumar2021/mcp-suite configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Abhishekkumar2021/mcp-suite. 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/Abhishekkumar2021/mcp-suite/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Abhishekkumar2021/mcp-suite

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/abhishekkumar2021/mcp-suite/claude-md/github.svg)](https://agentmods.dev/instructions/abhishekkumar2021/mcp-suite/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/abhishekkumar2021/mcp-suite/claude-md"><img src="https://agentmods.dev/badge/instructions/abhishekkumar2021/mcp-suite/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/abhishekkumar2021/mcp-suite/claude-md"><img src="https://agentmods.dev/badge/instructions/abhishekkumar2021/mcp-suite/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 4,684 This file is loaded in full into every session.

When invoked 4,684 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. ✓ AI security review Fable 5.1 · 7 Sept 2026 📄 Read the review

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	$0.04684	$0.04684
Opus 5.5	$0.01874	$0.01874
Sonnet 5.5	$0.00937	$0.00937
Haiku 4.5	$0.00468	$0.00468

Measured 2mo ago against content hash 322b69259e2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-suite 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 · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 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

mcp-suite is an npm-workspaces monorepo of independent Model Context Protocol servers written in TypeScript (ES modules). Each server in servers/<slug>/ is its own npm package (@abhishekmcp/<slug>), versioned and published independently, but shares root tooling (tsconfig.base.json, @types/node, typescript).

Commands

npm install                      # install deps for all workspaces (run once at root)
npm run build                    # build (tsc) every server
npm run build -w servers/notes   # build one server
npm run clean                    # rm -rf servers/*/dist

There is no test runner or linter configured. CI (.github/workflows/ci.yml) only runs npm run build across Node 18/20/22 — a clean tsc is the bar a change must clear. Verify servers with an ad-hoc stdio JSON-RPC smoke test: spawn node servers/<slug>/dist/index.js with the relevant env, write newline-delimited JSON-RPC to stdin (initialize → notifications/initialized → tools/list / tools/call), and parse responses from stdout line-by-line.

Hard constraints

stdout is the MCP transport. Never console.log from a server — log to stderr (console.error) only. A stray stdout write corrupts the protocol stream.
Prefer pure-JS / WASM dependencies. Servers run via npx @abhishekmcp/<slug> on any machine, so a pure-JS or WebAssembly library is always the default (portable, npm audit stays clean, no toolchain to build). A native dependency is allowed only when genuinely required (no viable pure-JS/WASM alternative), and must be gated + documented. Note the MCPB caveat: the bundle copies real node_modules, so any native .node binary is platform-specific and won't run on a different OS/arch from where it was packed. (The notes server deliberately uses MiniSearch instead of SQLite/FTS5, and hand-rolls its frontmatter parser to avoid js-yaml/npm-audit noise; the sql server uses sql.js (WASM) rather than better-sqlite3.)
Module resolution is Node16 ESM (tsconfig.base.json, "type": "module"). Relative imports must carry the .js extension even though the source is .ts.

Read the full file on GitHub · 172 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 · 172 lines · 4,684 tokens per session scan E 322b69259e2c

Subscribe to this mod's changes

mcp-suite CLAUDE.md is an instructions file published in the GitHub repository Abhishekkumar2021/mcp-suite (1 stars, last pushed 4mo ago), licensed MIT. It adds 4,684 tokens to every session, about $0.0187 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 claude llm-tools mcp model-context-protocol

mcp-suite CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-suite CLAUDE.mdAbhishekkumar2021/mcp-suite	Instructions file	1	4mo ago	MIT	A	4,684	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

mcp-suite: Instructions file for Claude Code