Airbyte Agents
by Airbyte
Official listing: built and published by Airbyte. More from Airbyte
Context layer for AI agents: MCP server and Python SDK giving agents unified access to 50+ business data connectors with pre-assembled context, reducing tool calls by 40–80%.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your assistant, with Airbyte Agents connected:
- Context Store Search
Use Airbyte Agents to search pre-assembled business context: ‹what you're looking for›
- Live Connector Reads
Use Airbyte Agents to fetch fresh data from source systems: ‹what you need›
Connect it over MCP
{
"mcpServers": {
"airbyte-agents": {
"url": "https://mcp.airbyte.com/mcp"
}
}
}claude mcp add --transport http airbyte-agents https://mcp.airbyte.com/mcp
In Grok, ChatGPT and other assistants, add a custom connector with the address https://mcp.airbyte.com/mcp (how, step by step).
It may ask you to sign in to Airbyte or for a key when you add it; the setup guide says which.
Setup guide: github.com/airbytehq/airbyte-agent-sdk
Call the API
Auth An API key from Airbyte
Setup guide: github.com/airbytehq/airbyte-agent-sdk
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- APIMCP
- Auth
- API Key
- Skills
- 3
Skills
Context Store Search
Search pre-assembled business context across Salesforce, HubSpot, Zendesk, Linear, Slack, and 45+ connectors before making live API calls.
Live Connector Reads
Fetch fresh data from source systems with write-back support to update records, tickets, and messages in the systems of record.
Agent SDK Integration
Integrate connectors into pydantic-ai, LangChain, OpenAI Agents, and FastMCP via typed Python decorators with built-in retry and error handling.