Connecting Mastra with Marketo Data via CData Connect AI MCP Server

Mastra is designed for developers and enterprise teams building intelligent, composable AI agents. Its modular framework and declarative architecture make it simple to orchestrate agents, integrate LLMs, and automate data-driven workflows. But when agents need to work with data beyond their local memory or predefined APIs, many implementations rely on custom middleware or scheduled syncs to copy data from external systems into local stores. This approach adds complexity, increases maintenance overhead, introduces latency, and limits the real-time potential of your agents.

CData Connect AI bridges this gap with live, direct connectivity to more than 300 enterprise applications, databases, ERPs, and analytics platforms. Through CData's remote Model Context Protocol (MCP) Server, Mastra agents can securely query, read, and act on real-time data without replication. The result is grounded responses, faster reasoning, and automated decision-making across systems all with stronger governance and fewer moving parts.

This article outlines the steps required to configure CData Connect AI MCP connectivity, register the MCP server in Mastra Studio, and build an agent that queries live Marketo data in real time.

Prerequisites

Before starting, make sure you have:

1. A CData Connect AI account
2. Node.js 18+ and npm installed
3. A working Mastra project (created via npm create mastra@latest)
4. Access to Marketo

Credentials checklist

Ensure you have these credentials ready for the connection:

1. USERNAME: Your CData email login
2. PAT: Connect AI, go to Settings and click on Access Tokens (copy once)
3. MCP_BASE_URL: https://mcp.cloud.cdata.com/mcp

Step 1: Configure Marketo connectivity for Mastra

Connectivity to Marketo from Mastra is made possible through CData Connect AI Remote MCP. To interact with Marketo data from Mastra, we start by creating and configuring a Marketo connection in CData Connect AI.

1. Log into Connect AI, click Sources, and then click Add Connection
👁 Adding a Connection

2. Select "Marketo" from the Add Connection panel
👁 Selecting a data source

3. Enter the necessary authentication properties to connect to Marketo.

   Both the REST and SOAP APIs are supported and can be chosen by using the Schema property.

   For the REST API: The OAuthClientId, OAuthClientSecret, and RESTEndpoint properties, under the OAuth and REST Connection sections, must be set to valid Marketo user credentials.

   For the SOAP API: The UserId, EncryptionKey, and SOAPEndpoint properties, under the SOAP Connection section, must be set to valid Marketo user credentials.

   See the "Getting Started" chapter of the help documentation for a guide to obtaining these values.

   👁 Configuring a connection (Salesforce is shown)
   
4. Click Save & Test
5. Navigate to the Permissions tab in the Add Marketo Connection page and update the User-based permissions. 👁 Updating permissions
   

Add a Personal Access Token

A Personal Access Token (PAT) is used to authenticate the connection to Connect AI from Mastra. It is best practice to create a separate PAT for each service to maintain granularity of access.

1. Click on the Gear icon () at the top right of the Connect AI app to open the settings page.
2. On the Settings page, go to the Access Tokens section and click Create PAT.
3. Give the PAT a name and click Create. 👁 Creating a new PAT
   
4. The personal access token is only visible at creation, so be sure to copy it and store it securely for future use.

With the connection configured and a PAT generated, we are ready to connect to Marketo data from Mastra.

Step 2: Set up the Mastra project

• Open a terminal and navigate to your desired folder
• Create a new project:

  npm create mastra@latest

👁 Creating a New Project

• Open the folder in VS Code
• Install the required Mastra dependencies:

  npm install @mastra/core @mastra/libsql @mastra/memory

• Then install the MCP integration package separately:

  npm install @mastra/mcp

Step 3: Configure environment variables

Create a .env file at the project root with the following keys:

OPENAI_API_KEY=sk-...
[email protected]
CDATA_CONNECT_AI_PASSWORD=your_PAT

Restart your dev server after saving changes:

npm run dev

Step 4: Add the CData Connect AI agent

Create a file src/mastra/agents/connect-ai-agent.ts with the following code:

import { Agent } from "@mastra/core/agent";
import { Memory } from "@mastra/memory";
import { LibSQLStore } from "@mastra/libsql";
import { MCPClient } from "@mastra/mcp";

const mcpClient = new MCPClient({
 servers: {
 cdataConnectAI: {
 url: new URL("https://connect.cdata.com/mcp/"),
 requestInit: {
 headers: {
 Authorization: `Basic ${Buffer.from(
 `${process.env.CDATA_CONNECT_AI_USER}:${process.env.CDATA_CONNECT_AI_PASSWORD}`
 ).toString("base64")}`,
 },
 },
 },
 },
});

export const connectAIAgent = new Agent({
 name: "Connect AI Agent",
 instructions: "You are a data exploration and analysis assistant with access to CData Connect AI.",
 model: "openai/gpt-4o-mini",
 tools: await mcpClient.getTools(),
 memory: new Memory({
 storage: new LibSQLStore({ url: "file:../mastra.db" }),
 }),
});

Step 5: Update index.ts to register the agent

Replace the contents of src/mastra/index.ts with:

import { Mastra } from "@mastra/core/mastra";
import { PinoLogger } from "@mastra/loggers";
import { LibSQLStore } from "@mastra/libsql";
import { connectAIAgent } from "./agents/connect-ai-agent.js";

export const mastra = new Mastra({
 agents: { connectAIAgent },
 storage: new LibSQLStore({ url: "file:../mastra.db" }),
 logger: new PinoLogger({ name: "Mastra", level: "info" }),
 observability: { default: { enabled: true } },
});

Step 6: Run and verify the connection

Start your Mastra server:

npm run dev

👁 Start your Mastra server


Step 7: Run a live query in Mastra Studio

In Mastra Studio, open the chat interface and enter one of the following sample prompts:

List available catalogs from my connected data sources.

👁 Run QUery in Mastra Studio


Build real-time, data-aware agents with Mastra and CData

Mastra and CData Connect AI together enable powerful AI-driven workflows where agents have live access to enterprise data and act intelligently without sync pipelines or manual integration logic.

Start your free trial today to see how CData can empower Mastra with live, secure access to hundreds of external systems.