How to Use the Kontak MCP in Mastra AI

Q: How do I use Kontak templates in Mastra AI?

Call listkontaktemplates to fetch available drafts. Your agent can then select the correct template ID and pass it into the messaging tool.

Build resilient messaging workflows with Mastra AI and the Kontak MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kontak MCP to Mastra AI

Create your Vinkius account to connect Kontak 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 Kontak with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated messaging logic in Mastra AI

Design agents that use `send_outbound_sms` within complex workflows. If a message fails, your Mastra agent handles the retry logic automatically based on your defined rules. This setup keeps your communication reliable. You define the flow, and the agent uses the tool to ensure messages reach their destination without manual oversight.

Conditional contact management

Program your agent to check `get_contact_details` before deciding on the next step in a sequence. It branches based on real data, ensuring your automation is always context-aware. Your logic stays clean because the agent handles the decision-making. It queries the server and reacts to the specific attributes returned for each contact.

Workflow-driven audit logging

Use `get_kontak_audit_logs` to trigger alerts when specific system events occur. Your workflow engine monitors these logs and executes follow-up actions like notifying an admin. This keeps your operations transparent. The agent watches the audit trail and reacts to anomalies, maintaining a log of all actions taken during the execution.

Setup guide

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

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

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

Initialize an MCPClient in your Mastra config pointing to the Kontak endpoint. Spread the tool list into your agent definition to grant it access to messaging functions.

Yes, you can define custom retry logic in your workflow. If `send_outbound_sms` encounters a transient error, the agent catches it and attempts the operation again.

The server operates in a secure sandbox. Only your specific client instance has access to the tools, and all data exchange is gated by your endpoint token.

Call `list_kontak_templates` to fetch available drafts. Your agent can then select the correct template ID and pass it into the messaging tool.

Yes, you can enable requireToolApproval for any sensitive operation. This forces a human to sign off before the agent actually sends an SMS or modifies data.

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