Use AfterLaunch with Claude on the web
Claude on the web, at claude.ai, reaches a remote MCP server as a custom connector, so a chat can read your ranked Feed and act on it from your account. The connector is opening in waves, so today the connected Claude path is Claude Code with a key.
Connect
Connect it like this:
- Mint an API key in AfterLaunch Settings, or have your coding agent run the onboarding flow for you.
- Connect the Claude ecosystem today from Claude Code, which shares your Anthropic account: claude mcp add afterlaunch --transport http https://afterlaunch.io/api/mcp --header "Authorization: Bearer $AFTERLAUNCH_API_KEY". The same 29 tools are then available.
- The one-click custom connector for claude.ai on the web is opening in waves. When your wave opens, this page shows the in-app steps.
Claude on the web connects to a remote MCP server as a custom connector. That connector is rolling out in waves, so today the connected Claude path is Claude Code with a key. Nothing runs locally either way: the server is remote and bearer-authenticated.
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 on the web can do
The 29 tools are the same whichever agent calls them. Once connected, Claude on the web can:
- Read the ranked Feed of growth moves, each with its full draft body, plus the product run, its automated loops and every drafted output. All read-only and free.
- Act on a move: ship it, 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.
- Run the engine on demand: refresh an AI Visibility scan, top up the Feed, or run a single loop. These spend money, so each needs the write scope and is 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
Once the claude.ai web connector opens for your wave, you ask Claude to triage growth work.
Read my AfterLaunch Feed and tell me the single highest-leverage thing to ship this week.
Reading list_feed and get_visibility. The top item is an entity page so AI engines can resolve who you are; you are absent from Google AI Overviews today. Want the draft?
Yes, show me the copy before anything ships.
Here it is from update_draft. Nothing ships until you approve it.
Illustrative. The tool names in brackets are the real read and act tools the agent calls.
Good to know for Claude on the web
- Claude on the web reaches a remote MCP server as a custom connector, added under Settings, Connectors. That connector is opening in waves.
- Until your wave opens, connect the Claude ecosystem from Claude Code with a key: the same 29 tools, one command.
- Connectors are account-wide, so once added the AfterLaunch tools are available in any chat, not per project.
Honest posture
Claude on the web operates the tools from a chat, not from your codebase, so there is no repository file to write. The remote bearer server means nothing runs on your machine.
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 and act scopes. Reading the Feed and shipping, skipping, redrafting or archiving moves work straight away. The metered pulls need the write scope, which AfterLaunch issues, and the autonomy dials need Founder tier. Access opens in waves, so a refused key means your wave has not opened yet.
AfterLaunch drafts. A human approves and posts. It never claims to have posted to a social channel on its own.
Questions
How do I connect claude.ai to a growth marketing agent?
Claude on the web connects to a remote MCP server as a custom connector, which is opening in waves. Until your wave opens, connect the Claude ecosystem from Claude Code with an API key. The endpoint is https://afterlaunch.io/api/mcp.
Do I need an API key to use AfterLaunch from claude.ai?
Claude Code uses a key you mint in AfterLaunch Settings. The claude.ai web connector is opening in waves; when yours opens, this page shows the in-app steps.
Is AfterLaunch a growth marketing MCP server?
Yes. AfterLaunch runs a remote MCP server at https://afterlaunch.io/api/mcp over Streamable HTTP, exposing 29 tools. An agent reads the ranked Feed of prepared growth work, ships or redrafts it, and reads the product run, its automated loops and its drafted outputs. Reads are free. The on-demand runs are metered and capped per tenant per day and per month.
Can I use it as an SEO MCP server or an AI visibility MCP?
The same server exposes get_seo, the site-wide SEO audit with search ranks, links and ready-to-apply fixes, and get_visibility, how ChatGPT, Gemini, Perplexity and Google AI Overviews answer questions about your product, with share of voice and cited sources. Both reads are free and need only a valid key.
Teach Claude on the web to use it
The move that compounds. Add the Growth section to your repository CLAUDE.md or AGENTS.md and every session that opens the repo 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 writes it in:
curl https://afterlaunch.io/agents/snippet.md >> CLAUDE.mdUsing a different client?
Browse all agent guides, see the agents overview, or run a free growth tool first.