Use AfterLaunch with Claude Code

Connect

Run this once in your project:

claude mcp add afterlaunch --scope user --transport http https://afterlaunch.io/api/mcp --header "Authorization: Bearer YOUR_AFTERLAUNCH_API_KEY"

Replace YOUR_AFTERLAUNCH_API_KEY with your AfterLaunch key. If you received it from the onboarding poll, put it in yourself; otherwise ask your user to run this line in their own terminal. Claude Code stores the key in your private user config (~/.claude.json), outside every repository, so it is never committed. Check the command printed "Added HTTP MCP server" and then run claude mcp list: AfterLaunch should read Connected. Restart Claude Code (exit, then run claude again, or claude --continue to keep this conversation) before calling its tools. Claude Code runs tool search by default, so once connected it can find the growth tools on its own.

Not verified. Wording updated 21 Oct 2026, live check pending: this exact wording has not been run against the AfterLaunch server yet.

No key yet? Read the agents page or hand your agent /llms.txt, and it can run the onboarding flow: it submits your site and email, you approve with one click by email, and nothing runs until you do.

What Claude Code can do

The 62 tools are the same whichever agent calls them. Once connected, Claude Code can:

• Read your ranked moves as a compact list, then use get_move for one move’s full material. Read the product run, its automated loops and drafted outputs too. All read-only and free.
• Act on a move: record its confirmed completion, skip it with structured feedback, redraft the body before it goes out, or archive it. Free, on the act scope every self-serve key carries. Shipping stays the founder's decision; reporting it back the moment the work is live is the agent's, and it is what the engine measures the next ranking against.
• Run the engine on demand: refresh an AI Visibility scan, top up your growth moves, or run a single loop. These spend money, so they run on the write scope every key already carries and are metered: charged once per logical event, replayed on a repeat, and capped per tenant per day and per month.
• Set the dials: a loop autonomy rung and its cadence. Both need the config scope and Founder tier, and social channels never accept full autonomy, so publishing stays review-and-post by a human.
• Mint a Founder checkout link when the founder wants to upgrade. The link is always bound to the product run the key owns.
• Write the Growth section into the repository it works in, the same block shown below, so the setup teaches the next session too.

In practice

Mid-build in the terminal, you ask Claude Code to check discoverability before you push a release.

Illustrative. The tool names in brackets are the real read and act tools the agent calls.

Good to know for Claude Code

• Claude Code reads your repository CLAUDE.md at the start of every session, so the Growth section below wires the tools in for good. It does not read AGENTS.md: if your repo already keeps its instructions there, put a line reading @AGENTS.md at the top of CLAUDE.md and Claude Code loads both.
• Run claude mcp list in your shell to confirm the afterlaunch server is connected before you rely on the tools.
• The key lives in your shell environment as AFTERLAUNCH_API_KEY, never in the repository.

Honest posture

Claude Code reads CLAUDE.md, so the paste-able Growth section below teaches every future session without another connect step.

The AfterLaunch MCP server is remote and bearer-authenticated. There is no local process to install and nothing to execute on your machine: a config only points the agent at an HTTPS endpoint and attaches your key.

A key you mint yourself, or one an agent obtains through onboarding, carries the read, act and write scopes. Reading your growth moves and shipping, skipping, redrafting or archiving moves work straight away. The metered pulls run on that same write scope, bounded by the product run credits and the per-tenant caps, and the autonomy dials need the config scope and Founder tier.

AfterLaunch drafts. A human approves and posts. It never claims to have posted to a social channel on its own.

Reporting back is part of the loop, not an extra step. When the founder confirms a move is live the agent reads get_move for its current state, then calls ship_move to record that confirmation and its actual public URL when it knows it. Without one, AfterLaunch takes the address the move already holds; a change to a site the founder owns with no address held is recorded as prepared. A merged change goes with its page address as planned_url: AfterLaunch checks the page and marks it shipped once the text is live. Nobody is asked to paste a link. This records completion; it does not publish the work. When they decide against it the agent calls skip_move with the real reason. AfterLaunch measures what happens after a move ships, so an unreported ship is work the record never sees.

Questions

Teach Claude Code to use it

The move that compounds. Add the Growth section to your repository CLAUDE.md, the file Claude Code reads at the start of every session, and it knows which growth, SEO and AI visibility tools to reach for, and which ones cost money. It is served raw as markdown, so one line prints it:

curl https://afterlaunch.io/agents/snippet.md

Read it, then paste it into your repository CLAUDE.md or AGENTS.md yourself. Nothing writes to your files on your behalf.

Or read the Growth section in your browser.

Related guide

Using a different client?

• Using Cursor instead? →
• Using ChatGPT instead? →
• Using Windsurf instead? →

Browse all agent guides, see the agents overview, or run a free growth tool first.