Kit.com MCP Server

io.github.dancumberland由 GitHub 账号 dancumberland 发布v1.0.1更新于 Oct 24, 2026

Agent-optimized MCP server for Kit.com email marketing. 13 composite tools, 100% V4 API.

概览

AI 生成的概览

本地 MCP 服务器,把助手连接到 Kit.com 邮件营销账户,处理订阅者、标签、广播和互动数据。

可以做什么
  • 查找、列出、创建、更新和退订订阅者,查看其统计并对比最多 100 人的互动情况
  • 列出、创建和更新标签,为订阅者打标签或移除标签,并列出已打标签的订阅者
  • 列出、获取、创建草稿、更新和删除广播,并查看广播统计、跨广播对比和单链接点击数据
  • 列出表单、序列、细分、邮件模板和 webhook,并把订阅者加入表单或序列
  • 创建和删除自定义字段与 webhook,获取含增长数据的账户概览
  • 执行订阅者、标签、表单和字段的批量操作,并测试 API 连接
适用场景
适合管理 Kit.com(原 ConvertKit)邮件列表的人:用自然语言询问列表增长、订阅者互动、广播表现和链接点击情况,或完成打标签、创建广播草稿等日常操作,无需打开 Kit 后台。
运行要求
通过 npx 在本地运行,需要 Node.js 22 或更高版本。需要 Kit.com 账户(免费或付费)以及通过 KIT_API_KEY 设置的 Kit API 密钥;购买和批量操作还需可选的 KIT_OAUTH_TOKEN。需要访问 Kit V4 API 的网络连接。
安装前请注意
服务器在其环境配置中保存 Kit API 密钥,可能还有 OAuth 令牌;能访问该配置的人即可操作你的 Kit 账户。许多工具会修改数据:创建、更新、退订和给订阅者打标签,创建和删除广播、自定义字段与 webhook,以及每次最多 1 万条的批量操作。创建广播只生成草稿,但删除和批量修改无法撤销。订阅者数据会发送到 Kit API。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Kit.com MCP Server,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

@dancumberland/kit-mcp

The most complete MCP server for Kit.com (formerly ConvertKit). 13 agent-optimized tools covering 100% of the Kit V4 API — including engagement analytics, bulk operations, and broadcast click tracking that no other Kit MCP offers.

How This Is Different

Other Kit MCP servers wrap each API endpoint as a separate tool (29+ tools). That approach breaks in practice:

@dancumberland/kit-mcpOther Kit MCPs
Tool count13 composite tools (45 actions)29+ individual tools
Engagement analyticsPer-subscriber open/click rates, batch comparison across 100 subscribers, engagement-based filteringNone
Broadcast analyticsPer-broadcast stats, cross-broadcast comparison, per-link click trackingBasic list/get only
Bulk operationsBatch create subscribers, tags, form subscriptions (up to 10k per call)None
Response formatFormatted text summaries (agent-friendly)Raw JSON (agent must parse)
Rate limitingSliding window with automatic retry + exponential backoffNone
Error recoveryTyped errors with actionable recovery hintsGeneric errors
Cursor compatible13 tools (well under 40-tool limit)29+ tools (risks hitting limit)
Token overhead~3,200 tokens for all tool definitions~8,000+ tokens

Engagement Analytics (Exclusive)

This is the only Kit MCP that can answer "who are my most engaged subscribers?":

> Find my most engaged 100 subscribers who've been on my list over 6 months
Subscriber Comparison (100 of 100 loaded, sorted by open rate):
  1. Alice <[email protected]> — Open: 82.3% | Click: 24.1% | Sent: 95 | Last open: 2026-03-15 (ID: 456)  2. Bob <[email protected]> — Open: 71.0% | Click: 18.5% | Sent: 102 | Last open: 2026-03-14 (ID: 789)  ...

Other Kit MCPs can list subscribers and get basic profiles, but can't fetch engagement stats, compare across subscribers, or filter by engagement metrics.

What This Does

Connects any MCP client (Claude Desktop, Claude Code, Cursor, Windsurf, etc.) to your Kit.com email marketing account. Ask questions naturally:

  • "How many subscribers do I have and how's my list growing?"
  • "Show me my broadcast stats from last week"
  • "Find my most engaged subscribers from the past 6 months"
  • "Tag everyone who signed up through my landing page"
  • "Create a draft broadcast for my newsletter"
  • "Which links got the most clicks in my last broadcast?"

No coding required — just set it up and start talking.

Prerequisites

  1. Node.js 22+ — Download from nodejs.org. Check with node --version.
  2. A Kit.com account — Free or paid, any plan.
  3. Your Kit API key — kit.com → Account Settings → Developer. Starts with kit_.

Setup: Claude Desktop App (Recommended)

Step 1: Find your config file

Mac:

bash
open ~/Library/Application\ Support/Claude/

Open claude_desktop_config.json in any text editor.

Windows:

%APPDATA%\Claude\claude_desktop_config.json

Step 2: Add the Kit MCP server

If the file is empty or doesn't exist, paste this (replace your-kit-api-key with your actual key):

json
{  "mcpServers": {    "kit": {      "command": "npx",      "args": ["-y", "@dancumberland/kit-mcp@latest"],      "env": {        "KIT_API_KEY": "your-kit-api-key"      }    }  }}

If you already have other MCP servers, add "kit" inside the existing "mcpServers" block with a comma after the previous entry.

Step 3: Restart Claude Desktop

Fully quit (not just close the window) and reopen.

Step 4: Verify it works

Test my Kit connection

Claude should respond with your account name, auth method, and rate limit.

Setup: Claude Desktop with Cowork

Cowork is Claude Desktop's background agent. After completing the setup above, Cowork automatically has access to your Kit tools.

Example tasks:

  • "Every morning at 8am, summarize my subscriber growth and email performance from the last 24 hours."
  • "Every Monday at 9am, compare my broadcast stats from the past week — open rates, click rates, and unsubscribes."
  • "Every Friday, list all tags with fewer than 10 subscribers (candidates for cleanup)."

Setup: Claude Code (CLI)

Add to .claude/settings.local.json or ~/.claude/settings.json:

json
{  "mcpServers": {    "kit": {      "command": "npx",      "args": ["-y", "@dancumberland/kit-mcp@latest"],      "env": {        "KIT_API_KEY": "your-kit-api-key"      }    }  }}

Setup: Cursor

  1. Open Settings (Cmd+,)
  2. Search for "MCP"
  3. Click "Add MCP Server"
  4. Add:
json
{  "kit": {    "command": "npx",    "args": ["-y", "@dancumberland/kit-mcp@latest"],    "env": {      "KIT_API_KEY": "your-kit-api-key"    }  }}

Tools

ToolActionsWhat You Can Do
manage_subscribers10Find, list, create, update, unsubscribe, view stats, compare engagement across up to 100 subscribers, find top engaged subscribers in one call, filter by status/tags, filter by engagement metrics
manage_tags6List, create, update, tag/untag subscribers, list tagged
manage_broadcasts8List, get, create drafts, update, delete, view stats, compare stats across broadcasts, analyze per-link click data
manage_forms3List forms, list subscribers, add subscriber
manage_sequences3List sequences, add subscriber, list subscribers
manage_custom_fields4List, create, update, delete
manage_purchases3List, get, create (OAuth required)
manage_segments1List segments
manage_webhooks3List, create, delete
manage_email_templates1List templates
get_account—Full account overview with email and growth stats
test_connection—Verify your API key works
bulk_operations7Batch subscriber/tag/form/field operations (OAuth required)

Things You Can Ask

What You SayWhat Happens
"How's my email list doing?"Account stats, subscriber count, growth trends
"Find [email protected]"Subscriber profile with tags, custom fields, engagement stats
"Who are my most engaged subscribers?"Engagement-filtered list ranked by open/click rates
"Show me my recent broadcasts"Broadcasts with status (draft/scheduled/sent)
"How did my last broadcast perform?"Open rate, click rate, unsubscribes, per-link click data
"Which links got the most clicks?"Per-link click analytics for any broadcast
"Compare my broadcast performance"Side-by-side stats across all broadcasts
"Create a tag called vip-customers"Creates the tag in Kit
"Tag [email protected] with vip-customers"Applies the tag
"Draft a broadcast with subject 'Big News'"Creates a draft (doesn't send)

Authentication

API Key (covers most features): Get at kit.com → Developer. Set as KIT_API_KEY.

OAuth Token (optional, for purchases and bulk operations): Set KIT_OAUTH_TOKEN alongside your API key.

json
{  "env": {    "KIT_API_KEY": "your-api-key",    "KIT_OAUTH_TOKEN": "your-oauth-token"  }}

Rate limits enforced automatically: 120 req/min (API key) or 600 req/min (OAuth), with retry + backoff on 429s.

Architecture: Why 13 Tools Instead of 29+

Most MCP servers create one tool per API endpoint. For Kit's API, that means 29+ tools — which causes real problems:

  • Context bloat — 8,000+ tokens just for tool definitions, leaving less room for your actual conversation
  • Poor accuracy — AI tool selection degrades measurably beyond 20 tools (research)
  • Compatibility — Cursor has a hard limit of 40 tools across all servers; 29 tools from one server leaves almost no room for others

This server uses 13 composite tools with a discriminated action parameter. Same API coverage, 60% fewer tokens, better accuracy. Each tool groups related operations (e.g., all subscriber actions under manage_subscribers) so the AI picks the right tool on the first try.

Error Handling

Errors include recovery hints that Claude can act on:

Error 401: Invalid API keyRecovery: Check your KIT_API_KEY. Find your key at kit.com → Account Settings → Developer.
  • 429 (rate limit): Automatic retry with exponential backoff, up to 3 attempts
  • 5xx (server error): Automatic retry once
  • 422 (validation): No retry — returns the error immediately with a fix suggestion

Troubleshooting

ProblemSolution
"Cannot find module" or npx errorsMake sure Node.js 22+ is installed: node --version
"Invalid API key"Double-check your key at kit.com → Developer
Tools don't appear in ClaudeFully quit and restart Claude Desktop (not just close the window)
"requires OAuth authentication"manage_purchases and bulk_operations need KIT_OAUTH_TOKEN
Rate limit errorsAutomatic — the server retries with backoff. If persistent, wait 60 seconds

Development

bash
npm installnpm run dev          # Watch modenpm run build        # Production buildnpm test             # Unit tests (179 tests)npm run test:int     # Integration tests (requires KIT_API_KEY)npm run lint         # Biome checknpm run typecheck    # TypeScript check

License

MIT

来源:README.md,提交 e2bfa8e

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v1.0.1最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分