How to Use the Adikteev MCP in Claude Code

Q: How do I connect Claude Code to the Adikteev MCP server?

It's a single command in your terminal: claude mcp add --transport http adikteev-mcp -- . After that, you can run claude mcp list to check that the tools are available.

Q: How do I create a new Adikteev segment from a shell script using Claude Code?

You call the tool directly: claude mcp call adikteev-mcp createsegment --param '...'. You pass the segment details as parameters. It's designed for exactly this kind of headless scripting.

Automate Adikteev campaign monitoring and audience management right from your terminal with Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Adikteev MCP to Claude Code

Create your Vinkius account to connect Adikteev 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 Adikteev with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get daily campaign reports in CI/CD

The `get_reporting` tool gives you raw campaign performance data. You can call it directly from a shell script or a CI/CD pipeline using `claude mcp call adikteev-mcp get_reporting`. Pipe the JSON output to `jq` to format it, then send it to a Slack channel. Set it up as a cron job and you've got automated daily reporting without anyone lifting a finger.

Sync audience segments from a script

This MCP Server is built for headless automation. You can write a shell script that uses `list_segments` and `create_segment` to sync audiences from an external data source. It's all command-line, so it runs anywhere. There's no UI to get in the way. It's perfect for backend processes where you need to manage marketing audiences programmatically.

Set up headless churn monitoring

With the `get_churn_scores` tool, you can build your own monitoring system. Write a simple script that runs on a schedule, calls the tool via Claude Code, and parses the output. If a high-value user's churn score passes a certain threshold, your script can trigger a PagerDuty alert or log an event. This is active monitoring, not passive dashboard checking.

Setup guide

Set up Adikteev 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 adikteev-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http adikteev-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 Adikteev 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": {
    "adikteev-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 Adikteev. 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 Adikteev 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 Adikteev MCP in Claude Code

It's a single command in your terminal: `claude mcp add --transport http adikteev-mcp -- `. After that, you can run `claude mcp list` to check that the tools are available.

Yes, that's a primary use case. Since Claude Code is a CLI, you can install it in a pipeline runner and call any Adikteev tool like `get_reporting` as a step in your CI/CD workflow.

You call the tool directly: `claude mcp call adikteev-mcp create_segment --param '...'`. You pass the segment details as parameters. It's designed for exactly this kind of headless scripting.

The tools on this MCP server return structured JSON to stdout. This makes it easy to pipe the output to other command-line utilities like `jq` for parsing or `tee` to log to a file.

Your data, such as churn scores and audience lists, is streamed over a secure transport you define with the `claude mcp add` command. Claude Code itself doesn't store anything; the data is passed through to stdout or stderr and it's up to your script to handle it. The connection is point-to-point and ephemeral.

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