How to Use the Airbyte MCP in Mastra AI

Q: How do I hook up Mastra AI to my Airbyte server?

Install @mastra/mcp@latest and register the Vinkius URL in your client configuration. Spread the tools from mcpClient.listTools() directly into your agent's tool array. The client handles transport negotiation automatically so you can immediately run listconnections.

Q: Can Mastra AI automatically retry a failed Airbyte sync job?

Yes, you can wrap the listjobs tool inside a Mastra workflow step. If the tool output indicates a failed run, the step triggers a conditional branch that retries the sync up to three times.

Q: How do I enforce human-in-the-loop checks for Airbyte on Mastra AI?

Use Mastra's built-in requireToolApproval function on sensitive tools like getsource or getconnection. This halts the agent's execution and waits for a manual payload confirmation before reading your database connection details.

Q: Does Mastra AI support multi-workspace setups for Airbyte?

Yes, the agent can call listworkspaces to discover all active environments. You can then write a conditional workflow that routes specific sync commands based on the workspace ID returned by this MCP Server.

Build self-healing Airbyte pipelines with Mastra AI workflows and automated retries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Airbyte MCP to Mastra AI

Create your Vinkius account to connect Airbyte 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 Airbyte with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build self-healing Airbyte workflows in Mastra AI

Pipelines fail, but your team shouldn't have to wake up at 3 AM to restart them. With this MCP Server, your Mastra AI agent can call `list_jobs` to monitor active syncs and detect unexpected halts. If a job fails, the Mastra workflow engine triggers an automatic retry with exponential backoff to recover without human intervention. By using `get_connection`, the agent checks if the underlying network path is still valid before attempting a restart. This saves compute cycles and prevents hammering a database that is completely offline.

Guard Airbyte destination changes with Mastra AI approvals

Changing where your production data goes is risky business. When Mastra AI attempts to reconfigure a target using `list_destinations`, you can use the `requireToolApproval` hook to pause the workflow. The agent prepares the modification, sends a Slack notification to your admin, and waits for a manual click before executing. The agent uses `list_workspaces` to ensure the target destination resides within the correct corporate boundary. This prevents accidental data leaks to external cloud buckets during automated migrations.

Automate Airbyte source discovery with Mastra AI agents

When a new database is provisioned, Mastra AI can automatically register it as an active ingestion point. The agent runs `list_sources` to audit your current footprint, compares it against your cloud inventory, and uses `get_source` to verify the connection parameters. Because Mastra supports conditional branching, you can set up logic that says: if a source is PostgreSQL, configure a specific replication slot, then trigger a sync. This turns static data configurations into dynamic, event-driven pipelines.

Setup guide

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

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

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

Install `@mastra/mcp@latest` and register the Vinkius URL in your client configuration. Spread the tools from `mcpClient.listTools()` directly into your agent's tool array. The client handles transport negotiation automatically so you can immediately run `list_connections`.

Yes, you can wrap the `list_jobs` tool inside a Mastra workflow step. If the tool output indicates a failed run, the step triggers a conditional branch that retries the sync up to three times.

Use Mastra's built-in `requireToolApproval` function on sensitive tools like `get_source` or `get_connection`. This halts the agent's execution and waits for a manual payload confirmation before reading your database connection details.

Yes, the agent can call `list_workspaces` to discover all active environments. You can then write a conditional workflow that routes specific sync commands based on the workspace ID returned by this MCP Server.

Vinkius executes this server in a zero-trust, ephemeral V8 isolate sandbox. When Mastra AI queries `get_connection` to inspect sync schedules, the metadata is processed entirely in-memory and never stored on disk, keeping your network topologies secure.

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