How to Use the Blueshift MCP in Mastra AI

Q: How do I register Blueshift tools inside Mastra AI?

First, install @mastra/mcp and instantiate the client with your Vinkius MCP server URL. Then, call mcpClient.listTools() and spread those tools directly into your Mastra agent configuration.

Q: Does the Blueshift integration with Mastra AI support human-in-the-loop approval?

Yes, you can set requireToolApproval to true in Mastra AI. This forces the system to pause for human confirmation before running tools like createupdatecustomer.

Build automated marketing workflows with Mastra AI and Blueshift to trigger campaigns and track user events.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Blueshift MCP to Mastra AI

Create your Vinkius account to connect Blueshift to Mastra AI 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 Blueshift with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Event Tracking Workflows

The `track_event` tool logs custom user actions directly into your marketing pipeline. Mastra AI runs this tool inside structured workflows, letting you chain event tracking with conditional logic. If a user triggers a specific event, the workflow engine automatically decides the next action based on your predefined rules. You write the workflow in TypeScript, defining steps that retry automatically if the Blueshift API drops. By using this MCP Server, your agents can flag high-value actions and instantly update user histories without manual intervention.

Sync Segments and Profiles with Mastra AI

The `list_segments` and `create_update_customer` tools keep your marketing lists synchronized with actual user behavior. Your Mastra AI agent uses these tools to scan existing lists and modify profiles when users qualify for new campaigns. The framework's built-in workflow engine handles the execution order, ensuring data flows correctly between your databases. If a profile update fails, Mastra's exponential backoff kicks in to retry the operation. This keeps your segments clean and up-to-date without writing complex error-handling boilerplates.

Trigger Campaigns Based on Performance Reports

The `get_campaign_performance` and `list_campaigns` tools allow your agent to monitor active marketing runs. Your Mastra AI agent pulls these performance metrics to evaluate if a campaign meets its goals. If performance dips below your target, the workflow can trigger an automatic notification or adjust the campaign parameters. To set this up, call `listTools()` on your MCP client and spread them into your agent's toolset. You can also require manual approval before your agent executes any high-impact marketing actions.

Setup guide

Set up Blueshift MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Blueshift tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "blueshift-mcp-client",
  servers: {
    "blueshift-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Blueshift Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Blueshift tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Blueshift transactions"
);
console.log(result.text);

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 Blueshift. 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 Blueshift 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 Blueshift MCP in Mastra AI

First, install `@mastra/mcp` and instantiate the client with your Vinkius MCP server URL. Then, call `mcpClient.listTools()` and spread those tools directly into your Mastra agent configuration.

Yes, Mastra's workflow engine has built-in retries and exponential backoff. If you hit API rate limits while calling `track_event` or `create_update_customer`, the system pauses and retries automatically.

Yes, you can set `requireToolApproval` to true in Mastra AI. This forces the system to pause for human confirmation before running tools like `create_update_customer`.

The framework auto-detects the transport type, supporting both Server-Sent Events (SSE) and Streamable HTTP. It connects to your Vinkius-hosted endpoint without any manual transport configuration.

It doesn't store them at all. Your customer profiles, catalog items, and event logs flow directly through ephemeral V8 isolates hosting the MCP Server. Vinkius handles the authorization securely so your API tokens are never exposed to the agent framework.

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