How to Use the Kevel MCP in Mastra AI

Q: How do I initialize this server in Mastra AI?

Install @mastra/mcp@latest and create a new MCPClient with your server URL. Call mcpClient.listTools() and spread the results into your Agent's tool array. Mastra auto-detects the transport layer for you.

Q: Can I require human approval for Kevel actions?

Yes, you can set requireToolApproval in Mastra. Even though these are read operations, you might want a human to verify large listflights queries before the agent proceeds to the next workflow step.

Build resilient Mastra AI workflows that audit and manage your Kevel ad engine automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kevel MCP to Mastra AI

Create your Vinkius account to connect Kevel 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 Kevel with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Kevel Audits with Mastra AI

This MCP Server plugs the Kevel Management API directly into your Mastra AI workflows. You can build agents that run scheduled checks on your ad inventory using `list_campaigns` and `list_flights` to ensure nothing is under-delivering. If the API times out, Mastra automatically retries with exponential backoff. Your workflow won't crash just because a massive `list_creatives` request took too long to return.

Branching Logic for Ad Inventory

Connect your inventory checks to conditional logic. An agent can call `list_zones` and `list_sites`, then branch the workflow depending on whether specific ad slots are available or sold out. You define the failure states. If `get_campaign` returns a paused status, Mastra can route that data to an admin notification step rather than proceeding with the reporting pipeline.

Safe Advertiser Lookups via MCP Server

Pulling client data requires reliability. Your agent can execute `list_advertisers` to gather account IDs, then map those to specific `get_advertiser` calls across a massive list. Spread the MCP tools directly into your Agent configuration. Mastra handles the HTTP or SSE transport automatically, letting your agent focus on pulling `list_ad_types` without worrying about connection drops.

Setup guide

Set up Kevel 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 Kevel 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: "kevel-mcp-client",
  servers: {
    "kevel-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Kevel 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 Kevel. 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 Kevel 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 Kevel MCP in Mastra AI

Install `@mastra/mcp@latest` and create a new `MCPClient` with your server URL. Call `mcpClient.listTools()` and spread the results into your Agent's tool array. Mastra auto-detects the transport layer for you.

No, the current toolset only reads data. You can pull existing assets via `list_creatives` and `list_ads`, but you cannot push new images or modify active campaigns.

Mastra's built-in workflow engine takes care of this. If you hit an API limit while running `list_channels`, the framework automatically applies exponential backoff and retries the request.

Yes, you can set `requireToolApproval` in Mastra. Even though these are read operations, you might want a human to verify large `list_flights` queries before the agent proceeds to the next workflow step.

Vinkius isolates your campaign data and flight metrics entirely. The MCP Server runs in an ephemeral V8 sandbox, ensuring your Mastra workflows access the API through a strict zero-trust boundary.

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