By Homegrown data pipelines tend to turn brittle, and they need more robust, standardized infrastructure. AI agents, meanwhile, are limited to what their models can do until they get access to external tools. The open question is whether an AI assistant like Claude or ChatGPT can actually run your data pipelines.
In this interview on TFiR, Ian Alton, Product Manager at Airbyte, explains how the Model Context Protocol lets Claude or ChatGPT build, run and fix data pipelines.
Guest: Ian Alton, Product Manager at Airbyte
Show: The Agentic Enterprise
LinkedIn: Ian Alton
Watch the discussion on YouTube
Here is what every data engineer and platform team needs to know.
Technical Deep Dive
Q: How do I run data pipelines from Claude or ChatGPT with MCP?
Ian Alton, Product Manager at Airbyte, explains that the Airbyte MCP turns an assistant like Claude or ChatGPT into the interface used to run Airbyte. It connects your AI agents to your Airbyte organization. Sign-in works the same way as signing into Airbyte today, and the assistant then does the work.
“It’s very easy to sign in. You sign in the same way that you sign into Airbyte today, and your assistant can do all that work for you.” Ian Alton, Product Manager, Airbyte
Q: What replaces brittle homegrown data pipelines?
Alton says Airbyte has always been about moving data and breaking down the brittle data pipelines that tend to originate with homegrown solutions. The replacement is more robust and standardized infrastructure for moving data. The MCP extends that same infrastructure to AI agents.
“Airbyte has always been focused on moving data, specifically on breaking down the brittle data pipelines that tend to originate from homegrown solutions and providing more robust, standardized infrastructure for moving data.” Ian Alton, Product Manager, Airbyte
Q: What is the Model Context Protocol and how does it give AI agents access to external tools?
MCP stands for Model Context Protocol. It gives AI agents access to external tools beyond what the models can do on their own. Alton compares it to a USB for AI.
“You can think of it like a USB for AI.” Ian Alton, Product Manager, Airbyte
Q: What can an AI agent do with the Airbyte MCP, and how many connectors does it reach?
Alton says almost everything possible in Airbyte today can now be done through the MCP. That includes the same 700 connectors. The agent can use them to build, run and fix data pipelines, and it can read data, all from a chat with a natural language interface.
“Essentially, almost everything that you can do in Airbyte today, you can now do with the MCP.” Ian Alton, Product Manager, Airbyte
Resources & Documentation
- Airbyte MCP, the MCP that connects AI agents to an Airbyte organization
***
👇 Click to Read Full Raw Transcript
Swapnil Bhartiya: How is Airbyte leveraging MCP? And then we’ll talk about this new announcement.
Ian Alton: So the MCP is the Model Context Protocol, and basically it gives AI agents access to external tools beyond what those models are capable of. You can think of it like a USB for AI. So Airbyte has always been about moving data and specifically about breaking down the sort of brittle data pipelines that tend to originate with homegrown solutions and providing more robust and standardized infrastructure for moving your data. So the MCP that we’ve released is essentially the means by which you can turn something like Claude or ChatGPT into the interface that you use to run Airbyte. So it connects your AI agents to your Airbyte organization. It’s very easy to sign in. You sign in the same way that you sign into Airbyte today, and your assistant can do all that work for you. Why this matters to Airbyte? Essentially, almost everything that you can do in Airbyte today, you can now do with the MCP. It gives you access to those same 700 connectors that we already provide, and the agent can use those connectors and build those data pipelines directly. It can build them, it can run them, it can fix them. Okay. And it can read data all from a chat, all with the benefit of a nice natural language interface.
