▌BestMCPTools.org
Airbyte MCP logo

Airbyte MCP

Inspect and manage data-ingestion connections and syncs from an agent.

DatabaseFreemiumClaudeClaude CodeCursorAll ModelsModerate✓ Verified
Visit Tool

Last verified: September 20, 2026

Own Airbyte MCP? Boost it to the top.✦ Upgrade to Featured

Maintenance status

Repository link unavailable
Checked September 28, 2026

The GitHub link we had for this server no longer resolves.

How to Install Airbyte MCP

$uvx airbyte-mcp

Requires Claude Desktop, Cursor, Windsurf, or another MCP-compatible client.

Setup by client

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "airbyte-mcp": {
      "command": "uvx",
      "args": [
        "airbyte-mcp"
      ]
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "airbyte-mcp": {
      "command": "uvx",
      "args": [
        "airbyte-mcp"
      ]
    }
  }
}

VS Code (.vscode/mcp.json)

{
  "servers": {
    "airbyte-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "airbyte-mcp"
      ]
    }
  }
}

Claude Code (terminal)

claude mcp add airbyte-mcp -- uvx airbyte-mcp

Add any API keys or environment variables the server's README lists.

About Airbyte MCP

Airbyte's MCP server lets an agent list sources and destinations, check connection health, inspect sync history and trigger syncs. For data teams the value is diagnostic: when a downstream table is stale, the agent can trace whether the ingestion job actually ran instead of a human opening a second dashboard. It complements rather than replaces transformation-layer servers like dbt.

Airbyte MCP is a Database MCP server designed for developers, analysts, and data teams. It enables querying and managing databases from an AI assistant by exposing schema introspection and SQL execution as MCP tools. Key capabilities include schema introspection across tables and views, parameterised sql execution, read-only and read/write modes, and structured tool calls that work cleanly inside an LLM context. It integrates with Postgres, MySQL, SQLite, MongoDB, Redis, BigQuery, and Snowflake, and is best suited for developers, analysts, and data teams who need ad-hoc analytics without a bi tool.

Key Features

  • airbyte
  • elt
  • ingestion
  • pipelines
  • data-engineering

Pricing

Freemium: from Free (open source; Airbyte Cloud has paid tiers)

Pros & Cons

Pros

  • Lets the assistant write and run real queries instead of guessing
  • Read-only mode is safe to point at production-shaped data
  • Skips most ORM and CSV-shuffling boilerplate

Cons

  • Misconfigured permissions can expose sensitive data
  • Long-running queries need explicit timeouts
  • Schema drift requires reconnecting or refreshing context

Best For

  • Ad-hoc analytics without a BI tool
  • Drafting migrations and reviewing query plans
  • Letting non-SQL teammates ask questions of a database
  • Bootstrapping internal admin workflows

Our Take on Airbyte MCP

Most useful as the first stop when data looks stale. It answers "did the sync run" without leaving your agent. Pair it with dbt MCP for full pipeline visibility.

Frequently Asked Questions

Tags

#Database#airbyte#elt#ingestion#pipelines#data-engineering