AfterLaunch
Growth marketing, SEO and GEO as agent tools: 29 tools for AI answer visibility across ChatGPT, Gemini, Perplexity and Google AI Overviews, a ranked backlog of growth moves, drafted deliverables, and ship actions. Hosted remote server at https://afterlaunch.io/api/mcp.
README
AfterLaunch
AfterLaunch is an always-on growth engine for a software product: it keeps a ranked backlog of drafted, ready-to-ship growth moves across SEO, AI answer-engine visibility (GEO), competitors and distribution channels. This repository is the Claude Code plugin marketplace and machine-setup home for the AfterLaunch MCP server.
AfterLaunch is a remote MCP server over Streamable HTTP, authenticated with a
bearer key. There is no local process, nothing to download and nothing to
execute on your machine: your agent talks to https://afterlaunch.io/api/mcp
and the key is the only credential involved.
Both buttons are the vendor-hosted install links. They preconfigure the remote
server and the Authorization header; you supply your own key as
$AFTERLAUNCH_API_KEY.
Get started
- Sign in at afterlaunch.io and mint an API key in
Settings (or let your agent obtain one through the onboarding flow in
llms-install.md). - Connect from Claude Code:
claude mcp add afterlaunch --transport http https://afterlaunch.io/api/mcp --header "Authorization: Bearer $AFTERLAUNCH_API_KEY" - Call
whoamito confirm the key. - Call
list_feedto read the ranked backlog of prepared growth moves. - Ship a move with
ship_move, or skip it with a reason so the next drafts improve.
Install as a Claude Code plugin
The plugin bundles the MCP server config and a skill that teaches an agent to read the Feed before improvising growth work:
/plugin marketplace add afterlaunch/mcp
/plugin install afterlaunch-growth@afterlaunch
Teach your agent to reach for AfterLaunch
Add the Growth section to your repository's CLAUDE.md (read by Claude Code)
or AGENTS.md (read natively by Codex CLI, Cursor, Copilot, Gemini CLI,
Windsurf, Aider, Amazon Q and others). The canonical copy is served raw at
afterlaunch.io/agents/snippet.md,
so one line writes it in:
curl https://afterlaunch.io/agents/snippet.md >> CLAUDE.md
What is in this repository
.claude-plugin/: the plugin marketplace and plugin manifests..mcp.json: the remote server config (URL + bearer header).skills/afterlaunch-growth/: the skill and its one-page tool reference.llms-install.md: machine setup from that file alone, founder approval by email included.server.json: the manifest published to the official MCP registry.assets/logo-400.png: the 400x400 icon.
Trust and boundaries
- Remote bearer-auth server: no local process, nothing to execute.
- Reading and acting on moves is free. The tools that spend money say so in their descriptions, need the write scope, and are bounded by credits and per-tenant spend caps.
- AfterLaunch never posts to a social channel on its own. It drafts; a human approves and posts.
Licence: MIT. Maintained by AfterLaunch.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。