Quickstart

Three steps: key, connect, ask. Your agent handles everything after that — the server teaches it how App Store search works.

01Get a key

Create an account (email + password), then mint an API key in your dashboard.

The key is shown only once — the dashboard also shows usage and rotates or revokes keys. Free while in early access: 500 tool calls per day and 500 tracked keyword × app × storefront combinations.

02Connect your client

claude code

$ claude mcp add openaso --transport http https://openaso-806591819206.us-west1.run.app/mcp \
    --header "Authorization: Bearer YOUR_KEY"

Cursor, Windsurf, or anything MCP — same endpoint, same header:

mcp config (json)

{
  "mcpServers": {
    "openaso": {
      "type": "http",
      "url": "https://openaso-806591819206.us-west1.run.app/mcp",
      "headers": { "Authorization": "Bearer YOUR_KEY" }
    }
  }
}

x-api-key: YOUR_KEY works too if your client cannot set an Authorization header. The server is stateless Streamable HTTP — POST only, no session juggling.

03Ask for something real

Good first prompts, in rough order of ambition:

"Where does app 6446901002 rank for habit tracker in the US and UK?" — one rank call.
"Audit the App Store listing for <your app> in the US and propose better metadata" — the audit tool gathers listing, word pool, and scored keyword candidates in one call, then your agent drafts against coverage.
"Track our top 20 keywords daily and tell me when anything drops" — track_config + the managed daily snapshot run, then history dropsOnly=true any morning.

There is also a packaged optimize_metadata prompt on the server — the full playbook from audit to tracked verification.