How to Use the Mav MCP in Mastra AI

Q: How do I build a retry loop for Mav lead creation in Mastra AI?

You wrap the createlead tool inside a Mastra workflow block with exponential backoff configured. If the MCP Server is busy, the workflow retries the action automatically until it succeeds.

Q: Can a Mastra AI agent dynamically switch Mav playbooks?

Yes, your agent can call listplaybooks to see available campaigns, then use the MCP client to start the best one. This allows the agent to tailor the SMS approach based on lead source.

Q: Does Mastra AI support human approval before a Mav opt-out?

Yes, you can configure the optoutlead tool to require human-in-the-loop approval. The workflow pauses and alerts your team before final execution.

Q: How do I get a summary of a lead's recent SMS history?

Use the getlead tool within your agent's execution step to fetch the full contact profile. The agent can then analyze the conversation history to plan its next action.

Build resilient, multi-step SMS outreach workflows by connecting Mav to Mastra AI agents using this 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 Mav MCP to Mastra AI

Create your Vinkius account to connect Mav 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 Mav with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Branching SMS Playbook Workflows

The `get_playbook` tool retrieves the exact steps of your SMS campaign so your Mastra AI agent can decide what to do next based on lead behavior. If a lead doesn't reply within an hour, the workflow engine automatically triggers a branch to try a different approach. This setup lets you build complex follow-up logic that doesn't break. You get full control over the conversation path without writing messy nested code.

Resilient Lead Syncing with Auto-Retries

The `update_lead` tool synchronizes contact details and qualification status back to your database whenever a prospect responds. Mastra AI uses its built-in retry engine to ensure this MCP tool call succeeds even if your CRM experiences temporary downtime. This keeps your lead records clean and up to date. You never have to worry about losing qualification data due to network hiccups.

Automated Outreach Kill Switches

The `stop_playbook` tool halts an active SMS campaign immediately if a Mastra AI agent detects a negative response or an opt-out request. The workflow engine handles this transition smoothly, canceling scheduled follow-up steps. This prevents awkward double-texting that annoys prospects. Your agent acts as a guard dog, keeping your automated outreach polite and compliant.

Setup guide

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

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

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

You wrap the `create_lead` tool inside a Mastra workflow block with exponential backoff configured. If the MCP Server is busy, the workflow retries the action automatically until it succeeds.

Yes, your agent can call `list_playbooks` to see available campaigns, then use the MCP client to start the best one. This allows the agent to tailor the SMS approach based on lead source.

Yes, you can configure the `opt_out_lead` tool to require human-in-the-loop approval. The workflow pauses and alerts your team before final execution.

Use the `get_lead` tool within your agent's execution step to fetch the full contact profile. The agent can then analyze the conversation history to plan its next action.

Your CRM contact records and conversation logs are processed in an ephemeral V8 MCP sandbox. No persistent storage is used on our servers, keeping your customer data completely private.

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