MCP & API

ASO Your Agent Can Actually Run

Read keyword competition, tracked ranks and your action plan through the REST API. Generate and translate metadata, then apply accepted edits to a draft. Install the versioned MCP package directly from AppDrift or call the REST API.

Reviewable drafts · REST available · Any paid plan

REST — read your action plan
curl -H "Authorization: Bearer ad_live_..." \
  "https://appdrift-backend-1fabfc95f592.herokuapp.com/v1/action-plan"
REST API
Available on paid plans
Draft writes
Review before publishing
MCP server
Direct package download
7-day
Eligible Indie trial

Two ways in

Add the server, or call the API

Connect once and ask away — or curl it from anywhere. Full setup and the complete endpoint reference are in the docs.

REST — any language
curl -H "Authorization: Bearer ad_live_..." \
  "https://appdrift-backend-1fabfc95f592.herokuapp.com/v1/action-plan"
Read the MCP & API docs →

Building a platform that ships apps for customers? See the Store-Ops API →

Capabilities

Your ASO data, where your agent already lives

Read account data, generate proposals and update editable drafts. AI operations consume tokens. The API does not directly publish store listings.

Keyword Difficulty, On Demand

Request a computed competition score for App Store or Google Play keywords. This is not official search volume or a prediction of ranking success.

Live Rank Tracking

Read your apps’ tracked keywords and their latest store rank. Your agent can answer “where do I rank for meditation?” without you opening a dashboard.

Page-One Opportunities

Review tracked keywords ranked 11–30 and use their computed difficulty to prioritize an investigation. A position near page one does not guarantee an easy improvement.

Weekly Action Plan

Your whole prioritized ASO plan — keyword pushes, rank drops, review themes, competitor overtakes, localization gaps — as structured data an agent can reason over.

MCP for Claude & Cursor

Install the AppDrift-hosted package in a stdio MCP client such as Claude Desktop or Cursor. The setup guide includes a versioned download and checksum.

REST for Everything Else

Read data with GET requests; use POST for AI generation, translation and editable draft updates. AI operations consume tokens; review output before using it.

How it works

Three steps from key to answer

Create a key, choose the MCP package or REST, and request your account data.

01

Create an API key

Open the Developers area of your dashboard and mint a key. It’s shown in full once, tenant-scoped, and revocable any time.

one key
02

Connect the server

Install the versioned AppDrift package in your MCP client with Node.js 22 or later, or call REST with your bearer key.

any agent
03

Ask your agent

“What should I optimize this week?” Your agent reads your real ranks, opportunities, and action plan — and answers.

FAQ

MCP & API, answered

The appdrift-mcp package connects MCP clients to AppDrift account data, AI generation, translation and editable draft operations. Install it from npm with npx -y appdrift-mcp and Node.js 22 or later; AppDrift also hosts a versioned archive. The official MCP registry listing is still pending.

Create an API key in your dashboard Developers area. Add appdrift-mcp to your client configuration using the setup guide (npx -y appdrift-mcp). Node.js 22 or later is required. Start with account_status and list_apps; neither consumes AI tokens.

No. It supports reads, token-priced AI generation and translation, and applying accepted optimization fields to an editable AppDrift draft. Applying an optimization changes saved draft content. It does not directly publish to App Store Connect or Google Play; review and store publishing are separate steps.

API access is included on eligible paid plans, starting at Indie for $29 per month. AI endpoints consume tokens according to the operation. Account keys are tenant-scoped and revocable from the Developers page.

The appdrift-mcp package implements the Model Context Protocol for clients such as Claude Desktop and Cursor and installs from npm. The REST API works with HTTP clients, scripts and automation tools.

Give your agent the ASO data it's missing

Grab a key and wire AppDrift into Claude or Cursor in a couple of minutes.

Agent-Native ASO: App Store Optimization Your AI Can Drive

One-shot AI text generation is commoditizing fast — any founder can ask a chatbot for an app description. What can't be answered from a blank chat window is your live, longitudinal ASO reality: your latest observed ranks, which keywords are near page one, what your reviewers keep complaining about, and which competitor just overtook you. That data lives in AppDrift. The MCP server and REST API put it inside the agent you already build with, so optimization happens in the flow of work instead of in yet another dashboard tab.

The Model Context Protocol is the emerging standard for giving AI agents safe, structured access to external tools and data. The AppDrift MCP package installs from npm with npx -y appdrift-mcp and Node.js 22 or later; the official MCP registry listing is still pending. Once configured with your account key, its tools can be called by an MCP client. Ask "which of my keywords are closest to page one?" and it calls keyword tracking for you. Ask "what should I ship this week?" and it reads your ASO Autopilot action plan and summarizes the top moves.

Read Data, Review Draft Changes

The API can read account data, generate or translate metadata, and apply accepted optimization fields to an editable AppDrift draft. Generation and translation consume tokens according to the endpoint. Applying a draft changes saved content; it does not publish it to Apple or Google. Review the proposed fields before applying them, then use the separate connected-store publishing workflow when ready.

Read and Draft Tools, One Key

The package includes account reads and draft operations. Keyword difficulty returns legacy competition heuristics where store data is available; it does not measure search demand or predict rankings. Rank tracking returns your tracked keywords and their latest positions. Opportunities surfaces the tracked keywords ranked 11–30 for further investigation. The action plan hands over your whole prioritized to-do list — pushes, rank drops, review themes, competitor overtakes, localization gaps — as structured data. And list apps ties it together so the agent knows which apps it's reasoning about. Generation and translation return reviewable output; applying an optimization updates the draft. Authentication is a single tenant-scoped key you can revoke any time; a key only ever sees the account that created it.

Prefer Plain HTTP? So Does Your CI

Not every workflow runs through an agent. MCP tools are backed by authenticated REST endpoints — GET for reads and POST for generation, translation and draft updates — so you can pull keyword difficulty into a spreadsheet, wire rank checks into a CI job, post opportunities to Slack, or feed the action plan into your own BI stack. Same data, same key, any language. When you're comparing AppDrift to other ASO platforms, this openness is part of the story: see how it fits the wider toolkit in our rundown of ASO tools in 2026. API and MCP access is included on every paid plan — see pricing to get a key.