What is mcp-toolkit CLAUDE.md?

Repository-specific instructions for working on mcp-toolkit, a TypeScript monorepo of reusable middleware packages for MCP servers. A monorepo keeps several related packages in one repository, while MCP servers provide tools that other applications can call.

Use it when developing or reviewing mcp-toolkit packages, installing dependencies, building the TypeScript code, or running its tests.

It gives coding agents the project context and the correct commands, language settings, package-management rules, and testing expectations for this repository.

How Sagargupta16/mcp-toolkit configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Sagargupta16/mcp-toolkit. 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/Sagargupta16/mcp-toolkit/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Sagargupta16/mcp-toolkit

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/sagargupta16/mcp-toolkit/claude-md/github.svg)](https://agentmods.dev/instructions/sagargupta16/mcp-toolkit/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/sagargupta16/mcp-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/sagargupta16/mcp-toolkit/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/sagargupta16/mcp-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/sagargupta16/mcp-toolkit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,411 This file is loaded in full into every session.

When invoked 1,411 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	$0.01411	$0.01411
Opus 5.5	$0.00564	$0.00564
Sonnet 5.5	$0.00282	$0.00282
Haiku 4.5	$0.00141	$0.00141

Measured 12d ago against content hash 7445f6bea328, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-toolkit 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 12d 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 · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file stacks on top of the workspace root at C:\Code\GitHub\:

Root CLAUDE.md -- voice, rules, routing map, references, skills, slash commands, conventions.

Root MEMORY.md -- live facts across repos.

Root STATUS.md -- live PR/CI/security dashboard.

.claude/resources/ -- deep reference for collaboration, workflow, git, OSS, debugging, voice.

Read those first. The guidance below only adds repo-specific context -- it does not override anything in the root.

Project

Public monorepo of reusable middleware packages (@mcp-toolkit/*) for building production MCP servers with the TypeScript SDK: auth, cache, rate-limit, logger, cors.

Beta (v0.3.3). Not yet published to npm -- users clone and build from source. The @mcp-toolkit npm scope is an existing npm org Sagar is not a member of (npm team ls mcp-toolkit returns 403), so publishing under these names fails; the scope (join the org or rename, e.g. @sagargupta1610/*) must be settled before any release workflow is added.

Stack

Language: TypeScript 7 (compiles to CommonJS -- no "type": "module", tsconfig module: Node16), Node >= 20
Framework: none -- plain library packages; peer dep @modelcontextprotocol/sdk >= 1.0
Database: none
Package manager: npm workspaces (see Repo-specific rules)
Deploy target: none yet -- npm publish blocked on the scope (see above); CI via shared reusable workflows

Run

npm install
npm run build        # tsc across all workspaces
npm run typecheck    # root tsc --noEmit (excludes examples/)
npm run lint         # per-package tsc --noEmit (no ESLint/Biome)
npm run typecheck:examples   # examples/ only; needs a build first
npm run bench        # bench/overhead.ts, middleware overhead per call; needs a build first
node scripts/check-release.mjs [vX.Y.Z]   # manifests, CHANGELOG heading and tag agree

Read the full file on GitHub · 75 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.

12d ago Changed 7445f6bea328
14d ago Changed 89484c978530
15d ago Changed · +1 lines · +39 tokens per session 3a90274b122b
19d ago Changed · +8 lines · +377 tokens per session f7a0ccb62947
2mo ago Changed · +3 lines · +275 tokens per session d5c93884b28d
2mo ago First seen · 63 lines · 720 tokens per session scan A e82fc94a6a0c

Subscribe to this mod's changes

mcp-toolkit CLAUDE.md is an instructions file published in the GitHub repository Sagargupta16/mcp-toolkit (4 stars, last pushed 6d ago), licensed MIT. It adds 1,411 tokens to every session, about $0.0056 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-tools authentication caching logging mcp middleware

mcp-toolkit CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-toolkit CLAUDE.mdSagargupta16/mcp-toolkit	Instructions file	4	6d ago	MIT	A	1,411	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-toolkit: Instructions file for Claude Code