How to Use the LeadConnector MCP in Mastra AI

Q: How do I connect LeadConnector to my Mastra AI agents?

Install the @mastra/mcp@latest package and initialize the client. Call listTools() on your instance, register the MCP server URL, and spread the tools directly into your agent's tool configuration array.

Build resilient, multi-step LeadConnector workflows using Mastra AI agents.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LeadConnector MCP to Mastra AI

Create your Vinkius account to connect LeadConnector 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 LeadConnector with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run failsafe pipeline audits with Mastra AI

Workflows break when HighLevel API limits hit or networks lag. Mastra AI handles this by wrapping your LeadConnector tools in a resilient workflow engine. When your agent triggers `list_opportunities`, the framework automatically manages retries with exponential backoff if the server rate limits you. You write the business logic in Mastra AI, and the framework ensures the execution completes. It is a bulletproof way to audit LeadConnector sales pipelines without babysitting API calls.

Conditional branching for calendar scheduling

Scheduling is rarely a straight line in HighLevel. This MCP Server lets your Mastra AI agent fetch calendar data using `list_appointments` and then branch based on what it finds. If a slot is taken, the agent automatically triggers a secondary lookup workflow. You define these steps in pure TypeScript using Mastra AI. The framework coordinates the transitions, making sure your booking agent behaves logically even when LeadConnector calendar states change mid-run.

Automate contact validation pipelines

Processing bulk contacts in HighLevel requires tight control over data flow. Mastra AI lets you build multi-step agents that pull batches using `list_contacts` and run them through validation filters. If a record fails validation, the MCP agent halts the Mastra AI workflow and flags it for human review. It keeps your LeadConnector CRM clean without requiring manual data entry.

Setup guide

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

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

const result = await agent.generate(
  "List recent LeadConnector 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 LeadConnector (GoHighLevel). 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 LeadConnector 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 LeadConnector MCP in Mastra AI

Install the `@mastra/mcp@latest` package and initialize the client. Call `listTools()` on your instance, register the MCP server URL, and spread the tools directly into your agent's tool configuration array.

Yes. You can use the framework's human-in-the-loop features to pause workflows. For example, before acting on data from `list_opportunities`, you can require an admin to sign off in the console.

The framework has built-in retry mechanisms with backoff. If a call to `list_contacts` triggers a rate limit error, the agent pauses and retries the request automatically without crashing your process.

Yes. The client automatically detects the transport type, whether it is Streamable HTTP or Server-Sent Events. This ensures a stable connection between your workflow engine and the server.

Your appointments, opportunities, and contact details are processed strictly in-memory during the workflow run. The MCP Server uses sandboxed V8 isolates, meaning no data is written to disk or stored externally.

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