MetaRun

› reprice Nutrio Pro yearly on the PPP index

175 territories computed · IN $5.99 · BR $9.99 · GB $21.99

✓ applied · recorded in change history · revertible

Live specimen: Nutrio repriced from an IDE session

The Model Context Protocol is the standard that lets AI coding agents call external tools. An MCP server for App Store Connect turns store operations (set a price, edit metadata, attach a build, submit for review) into tools your agent can call mid-conversation, which means release chores become sentences in the same session where you wrote the code.

The open-source options are local processes wrapping the raw API: you clone a repo, hand it your.p8 key, and get thin endpoints with no safety layer. MetaRun's server is the other kind: hosted, credential-secured, and built from the same 245 production tools that power its dashboard and AI operator, preview gates included.

The release ritual, from inside the editor

The last hour of every release is the same: bump the version, write What's New, translate it, check the screenshots, attach the build, submit. With the MCP server connected, that is a conversation: your agent drafts What's New from the changelog it just helped you write, stages it across locales, attaches the processed build, and walks the submission, previewing each step for your approval.

It also compounds with your own automation: agents can read your tracked ASO keywords before writing metadata, check territory pricing before a launch, or pull review sentiment while triaging issues, because reads are free-flowing and only writes are gated.

Letting an agent near your store, safely

The obvious objection is the right one: an AI agent with store credentials is a hazard. The design answer is that the agent never holds credentials and never holds unilateral write power. Authentication is a revocable personal access token (stored as a hash, shown once). Credentials stay server-side. Every mutation requires the preview's confirm token, drift on the store invalidates it, and destructive submissions require explicit acknowledgment flags.

Everything an agent applies lands in the same change history as manual and chat edits, attributed as MCP, and is revertible in one tap. You get the leverage of agentic operation with a paper trail and an undo.

Keys envelope-encryptedPreview before every writeOne-tap revert

What is an App Store Connect MCP server?

A Model Context Protocol server that exposes App Store Connect operations as tools AI agents can call. MetaRun hosts one with its full 245-tool surface, so your IDE's agent can manage pricing, metadata, screenshots, and releases without you leaving the editor.

How do I connect Claude Code to App Store Connect?

Can an AI agent submit my app for review?

Yes, deliberately and never silently: submission requires a preview, a confirm token, and an explicit acknowledgment flag on top. Your IDE also asks you to approve each tool call. The agent proposes; you dispose.

Is it safe to let an AI agent touch my App Store account?

The agent never sees your credentials: the token maps to your account server-side, where your key stays envelope-encrypted. Every write previews first, applies only with a fresh confirm token, is logged to change history, and is revertible in one tap.

Do I need to run the MCP server locally?

No. Open-source App Store Connect MCP servers run as local processes with your.p8 key on disk. MetaRun's is a hosted remote endpoint: one add command, token auth, zero local setup, and your key never touches your machine.

Anything that speaks MCP over Streamable HTTP: Claude Code, Cursor, and the growing set of MCP-capable clients. If your tool can add a remote MCP server with a bearer token, it can drive your App Store.

Reprice all 175 countries, edit metadata in every locale, render and publish screenshots, manage TestFlight and builds, cut and submit releases, respond to reviews, and track ASO keywords: the full MetaRun tool surface, reads unrestricted and writes preview-gated.

Are there ready-made workflows my agent can follow?

Yes: the open-source metarun-skills pack (claude plugin marketplace add metarun/metarun-skills) teaches agents five complete missions, from finishing a release after the build uploads to a full ASO audit. Every tool name in every skill is verified against the live registry on each build, so skills cannot go stale.

Change app, IAP, and subscription prices across all 175 App Store countries in one staged pass.

Design 3D device mockups with brand-aware templates and publish straight to App Store Connect.

Bulk-edit every locale of your listing with preview, apply, and one-tap revert.

npx metarun: the whole tool surface from a plain shell, no keys on your machine.

Spimov AI Video Dubbing MCP Server - Youtube Dubbing - Voice Clone

Dub any video into 600 languages — straight from your AI chat

Manage Meta, Google & TikTok ads — launch campaigns, track performance, spy on competitors, generate AI creatives.

GEO optimized content publishing engine for AI visibility

Launch & manage your User Referral and Partner / Affiliate program — for developers and growth teams.

Let AI clients add payments to your website. Create checkout pages, events and forms and embed them on your site in minutes.

Guides for making interactive videos & AI product demos that answer viewers' questions.

Scan how ChatGPT and Claude read your app, see who they name instead of you, and get the paste-ready fixes (llms.txt, JSON-LD, FAQ, meta) to get found.

Answers questions on AEO, SEO, web development and branding from the published material of GOJI, a Melbourne digital agency, with a goji.agency URL to cite on every result.