Agent guides

Use AfterLaunch with ChatGPT

ChatGPT reaches a remote MCP server through a custom connector rather than a file on disk. You add it once in settings, sign in, and the AfterLaunch tools are available inside a chat.

Connect

Connect it like this:

  1. Open ChatGPT settings, go to Security and login, and turn on Developer mode.
  2. Open the plugins directory at chatgpt.com/plugins and add a new plugin.
  3. Paste the server URL: https://afterlaunch.io/api/mcp
  4. Choose OAuth for authentication and sign in with your AfterLaunch account. There is no field for a static API key, so do not go hunting for one.
  5. Approve the AfterLaunch consent screen, then ask ChatGPT to read your AfterLaunch feed.

Developer mode is where custom MCP connectors live, and OpenAI keeps moving this surface, so the exact menu names shift between releases. The connectors section is now called plugins.

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 ChatGPT can do

The 53 tools are the same whichever agent calls them. Once connected, ChatGPT 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. 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 the Feed, 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

In a ChatGPT chat with the connector enabled, you ask for a read on your category.

You

How do ChatGPT, Gemini, Perplexity and Google AI Overviews describe my product versus my category?

ChatGPT

Running get_visibility. You are cited in Perplexity but missing from Google AI Overviews, and your share of voice is 12 percent. Reading list_feed for the fix ranked first.

You

Summarise the top three items and the effort each takes.

ChatGPT

From list_feed: an entity page (small), an FAQ schema block (small), and a comparison page (medium). Want the entity page drafted with update_draft?

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

Good to know for ChatGPT

  • Custom MCP connectors sit behind Developer mode, under Settings then Security and login. It is badged as elevated risk and it is off by default, but it is not limited to a paid plan.
  • OpenAI documents OAuth for an authenticated custom connector and offers no field for a static API key. Sign in when prompted rather than looking for a key box. Your AfterLaunch key still drives every other client on this page.
  • The connector runs inside a chat, not your codebase, so there is no repository file. The AfterLaunch tools appear in the chat composer once the connector is enabled.
  • ChatGPT reflows a tool result into its own prose rather than relaying the screen verbatim, so the answer you read is its summary of the board rather than the board itself.

Honest posture

ChatGPT operates the tools from a chat, not from your codebase, so there is no repo file to write. The remote server means nothing runs locally.

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 the Feed 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. 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.

Reporting back is part of the loop, not an extra step. When the founder confirms a move is live the agent calls ship_move, and 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

How do I connect ChatGPT to a growth marketing agent?

Turn on Developer mode under Settings then Security and login, add https://afterlaunch.io/api/mcp as a plugin from the plugins directory, and sign in when ChatGPT prompts you. OpenAI documents OAuth for an authenticated custom connector, and AfterLaunch runs that sign-in, so there is no key to paste.

Does the ChatGPT connector run inside my codebase?

No. ChatGPT operates the tools from a chat, so there is no config file to commit. The server is remote, so nothing runs on your machine.

Is AfterLaunch a growth marketing MCP server?

Yes, though the server is the door rather than the product. AfterLaunch is the agentic growth engine: it watches how the leading AI search engines answer about you, audits every page of your site, tracks your competitors and the communities and directories that decide whether you get found, and keeps the history. The remote MCP server at https://afterlaunch.io/api/mcp speaks Streamable HTTP and exposes 53 tools, so 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 ChatGPT to use it

ChatGPT works from a chat rather than a repository, so there is no instructions file to write and nothing to install. The connector above is the whole setup. If you also work in a terminal or an editor, the guides below add the Growth section to that repository, so both surfaces reach for the same tools.

Or read the Growth section in your browser.

Using a different client?

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