How to Use the AppFollow MCP in Claude Code

Q: How do I install the AppFollow MCP Server in Claude Code?

Run claude mcp add --transport http appfollow -- in your terminal. Make sure to place all flags before the server name. The configuration saves directly to your /.claude.json file.

Q: How does Claude Code read AppFollow reviews?

The terminal client calls the listreviews tool to fetch recent user feedback. You can pipe this output into jq or have the AI agent parse the text to find specific crash reports.

Pipe AppFollow MCP Server data into your terminal with Claude Code to automate review tracking, monitor app rankings, and trigger CI/CD alerts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AppFollow MCP to Claude Code

Create your Vinkius account to connect AppFollow to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup AppFollow with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger CI/CD alerts on chart drops

The `get_rankings` tool outputs your app's current store chart position directly to standard output. You can write a shell script that tells Claude Code to check this metric every morning and exit with a non-zero code if your app falls out of the top 100. Running headless in a GitHub Action, the CLI pulls context using `get_app_info` to format an alert payload. It grabs the exact ranking numbers and pipes them into your Slack or PagerDuty webhooks without requiring manual intervention.

Monitor reviews with the AppFollow MCP Server

The `get_reviews_ai_summary` tool delivers a concise breakdown of recent user feedback straight to your terminal. SREs can run a quick command to see if users are reporting crashes immediately after a production deployment. If the summary highlights an issue, you instruct the CLI to execute `list_reviews` for the raw text. Claude Code parses the JSON response, greps for specific error codes mentioned by users, and outputs the affected device types.

Track star metrics in shell scripts

The `get_ratings_history` tool fetches the timeline of your app's star average. DevOps teams use this to build automated reports that correlate rating dips with specific backend deployment timestamps. The CLI combines this with `get_reviews_summary` to get the total volume of feedback. You can dump this raw data into a CSV file or pipe it into a local database for long-term metric tracking.

Setup guide

Set up AppFollow MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see appfollow-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest AppFollow transactions." It will automatically discover and invoke the available AppFollow tools.

Terminal

claude mcp add --transport http appfollow-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the AppFollow MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "appfollow-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by AppFollow. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect AppFollow now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about AppFollow MCP in Claude Code

Run `claude mcp add --transport http appfollow -- ` in your terminal. Make sure to place all flags before the server name. The configuration saves directly to your ~/.claude.json file.

Yes. Since the CLI runs headless, you can schedule it to execute the `get_rankings` tool at specific intervals. It fetches the latest chart positions and can pipe the results to a log file.

The terminal client calls the `list_reviews` tool to fetch recent user feedback. You can pipe this output into jq or have the AI agent parse the text to find specific crash reports.

Use the claude mcp list command to verify the server is registered. Then, ask the agent to run the `get_account_check` tool to confirm the Vinkius endpoint is authenticating properly.

Vinkius routes your review summaries, chart positions, and rating histories through an ephemeral cloud sandbox. The terminal client only receives the requested data payload, and no persistent state remains on the proxy after the connection closes.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript