Use AfterLaunch with VS Code

VS Code, with GitHub Copilot in agent mode, connects to a remote MCP server through a small JSON file. Add one server and the AfterLaunch tools appear in the Copilot chat.

Connect

Add this to your .vscode/mcp.json (workspace) or your VS Code user settings:

{
  "servers": {
    "afterlaunch": {
      "type": "http",
      "url": "https://afterlaunch.io/api/mcp",
      "headers": {
        "Authorization": "Bearer ${input:afterlaunch_key}"
      }
    }
  },
  "inputs": [
    {
      "type": "promptString",
      "id": "afterlaunch_key",
      "description": "AfterLaunch API key",
      "password": true
    }
  ]
}

VS Code prompts for the key the first time the server starts and keeps it in the editor secret storage, so it never lands in the committed file. Reference it with the ${input:afterlaunch_key} placeholder shown above.

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 VS Code can do

The 29 tools are the same whichever agent calls them. Once connected, VS Code 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

In the VS Code Copilot chat in agent mode, you check discoverability without leaving the editor.

You

What growth work is queued, and how are AI engines answering about us?

VS Code

Reading list_feed and get_visibility. Five items are ready; the top is a set of SEO fixes from get_seo. You are cited in ChatGPT but missing from Perplexity.

You

Draft the SEO fixes and show me first.

VS Code

Drafting with update_draft. Review, then run ship_move when you are ready.

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

Good to know for VS Code

  • VS Code reads MCP servers from .vscode/mcp.json (workspace) or your user settings, using "type": "http" for a Streamable HTTP server.
  • Reference the key with an ${input:...} placeholder; VS Code prompts once and stores it in secret storage, so it never lands in the committed file.
  • The AfterLaunch tools appear in the Copilot chat tools picker in agent mode. Turn on MCP support in settings if your build gates it.

Honest posture

VS Code reads AGENTS.md natively, so the Growth section below teaches Copilot which tools to reach for. The server is remote and bearer-authenticated, so 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 VS Code and GitHub Copilot to a growth marketing agent?

Add an afterlaunch server to .vscode/mcp.json with "type": "http" and the url https://afterlaunch.io/api/mcp, plus an Authorization: Bearer header. VS Code prompts for the key on first run and stores it in secret storage.

Where does VS Code keep the AfterLaunch key?

Reference it with an ${input:...} placeholder and VS Code prompts once, keeping it in the editor secret storage rather than the committed mcp.json.

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 VS Code 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.md

Or read the Growth section first.

Using a different client?

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