mcp-kit CLAUDE.md

mcp-kit CLAUDE.md is an instructions file for coding agents from aplaceforallmystuff/mcp-kit. It costs 644 tokens per session, scanned A, original, MIT.

A project instruction document for MCP Kit, a server that connects AI assistants to Kit.com's email-marketing service. It explains the project structure, commands, data flow, and coding patterns.

In plain words
What is it for?
Use it when developing MCP Kit features for Kit.com subscribers, tags, email sequences, broadcasts, forms, custom fields, and webhooks.
Why use it?
It gives coding agents the repository context they need to install, build, run, and extend the server consistently.

Instructions file

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/aplaceforallmystuff/mcp-kit/claude-md
Clone the repo
git clone --depth 1 https://github.com/aplaceforallmystuff/mcp-kit

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 mcp-kit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/aplaceforallmystuff/mcp-kit/claude-md.svg)](https://agentmods.dev/instructions/aplaceforallmystuff/mcp-kit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/aplaceforallmystuff/mcp-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/aplaceforallmystuff/mcp-kit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 644 This file is loaded in full into every session.
When invoked 644 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 $0.00644 $0.00644
Opus 5 $0.00322 $0.00322
Sonnet 5 $0.00129 $0.00129
Haiku 4.5 $0.00064 $0.00064

Measured 4d ago against content hash 63cdc4030abc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-kit 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 4d 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 · 106 lines

How it starts

The opening of the file, as written. The whole thing — 106 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 when working with this repository.

Project Overview

MCP Kit is a Model Context Protocol server that provides tools for interacting with the Kit.com (formerly ConvertKit) email marketing API. It enables AI assistants to manage subscribers, tags, sequences, broadcasts, forms, custom fields, and webhooks.

Build and Development Commands

# Install dependencies
npm install

# Build TypeScript to JavaScript
npm run build

# Watch mode for development
npm run dev

# Run the server
npm start

Architecture

src/
├── index.ts      # MCP server setup, tool definitions, request handlers
└── kit-client.ts # Kit.com API v4 client with typed methods

Data Flow

  1. MCP client sends tool request →
  2. index.ts validates parameters with Zod →
  3. KitClient makes authenticated HTTP request to Kit.com API v4 →
  4. Response formatted and returned to MCP client

Key Patterns

Tool Registration:

server.tool(
  "tool_name",
  "Tool description",
  { /* Zod schema for parameters */ },
  async (params) => {
    // Implementation
  }
);

API Client Methods:

  • All methods in kit-client.ts handle authentication via X-Kit-Api-Key header
  • Pagination uses cursor-based approach (after, per_page)
  • Returns typed PaginatedResponse<T> for list operations

Adding New Tools

  1. Add the API method to kit-client.ts
  2. Register the tool in index.ts with appropriate Zod schema
  3. Follow existing patterns for error handling and response formatting
  4. Rebuild with npm run build

Environment Variables

Variable Required Description
KIT_API_KEY Yes Kit.com API v4 key

API Reference

This server uses Kit.com API v4. Documentation: https://developers.kit.com/

Tool Categories

Category Tool Count Description
Account 1 Account information
Subscribers 7 CRUD + tag management
Tags 6 CRUD + subscriber listing
Sequences 3 List, get, add subscribers
Broadcasts 5 Full CRUD
Forms 3 List, get, add subscribers
Custom Fields 1 List fields
Webhooks 3 CRUD

Read the full file on GitHub · 106 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. 4d ago First seen · 106 lines · 644 tokens per session scan A 63cdc4030abc

Subscribe to this mod's changes

mcp-kit CLAUDE.md is an instructions file published in the GitHub repository aplaceforallmystuff/mcp-kit (4 stars, last pushed 3mo ago), licensed MIT. It adds 644 tokens to every session, about $0.0032 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.