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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.