How to Use the Airbyte MCP in CrewAI

Q: How do I pass this Airbyte MCP Server to a CrewAI agent?

Pass the Vinkius HTTP URL directly into the agent's mcps array during initialization. The agent automatically discovers tools like listconnections and knows when to call them during its execution cycle.

Q: Can I restrict a CrewAI agent to read-only Airbyte tools?

Yes, use MCPServerHTTP from the crewai.mcp package and apply a toolfilter. This lets you expose safe tools like listjobs while completely hiding configuration tools like getsource.

Q: How does this MCP Server protect my Airbyte database credentials?

Every tool execution, such as getsource, runs inside a secure, ephemeral V8 isolate sandbox on Vinkius. No database credentials or workspace secrets are ever cached, ensuring your pipeline configurations remain strictly confidential.

Deploy a cooperative CrewAI team of agents to monitor and manage your Airbyte syncs.

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 CrewAI

Create your Vinkius account to connect Airbyte to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate multi-agent Airbyte audits with CrewAI

Running a complex data warehouse requires specialized roles. With CrewAI, you can assign one agent to act as a Pipeline Auditor using `list_connections` to monitor sync schedules, while a second agent acts as an Infrastructure Specialist. When the auditor spots a lag, it passes the connection ID to the specialist to run deeper diagnostics. The specialist agent runs `list_jobs` to extract the exact error logs from the failed sync. Because CrewAI agents share memory, they collaborate on the root cause without repeating API queries.

Manage multi-workspace Airbyte setups using CrewAI teams

Large enterprises run data pipelines across dozens of isolated environments. Your CrewAI manager agent can call `list_workspaces` to map out the entire organization, then delegate specific workspaces to subordinate agents. Each sub-agent takes ownership of a workspace, monitoring the local data flows autonomously. These sub-agents run `list_sources` to catalog every database feeding into their assigned workspace. If a new database is added, they notify the manager agent to update the master architecture map.

Run autonomous Airbyte failover operations with CrewAI

When a destination database goes offline, your data pipeline can stall for hours. A CrewAI agent team can detect this immediately using `list_destinations` to check target health. If a failure is found, a recovery agent queries `get_source` to identify the data origin and pauses active ingestion to prevent data loss. The recovery agent then uses `get_connection` to check if an alternative replica destination is available. This allows your team to automate disaster recovery without waiting for a database administrator to log in.

Setup guide

Set up Airbyte MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Airbyte tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Airbyte Analyst",
    goal="Access and analyze Airbyte data via MCP.",
    backstory="Expert analyst with direct Airbyte access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Airbyte transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Airbyte Analyst",
        goal="Access and analyze Airbyte data via MCP.",
        backstory="Expert analyst with direct Airbyte access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Airbyte transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass the Vinkius HTTP URL directly into the agent's `mcps` array during initialization. The agent automatically discovers tools like `list_connections` and knows when to call them during its execution cycle.

Yes, use `MCPServerHTTP` from the `crewai.mcp` package and apply a `tool_filter`. This lets you expose safe tools like `list_jobs` while completely hiding configuration tools like `get_source`.

CrewAI agents use a shared memory system. When the monitoring agent calls `list_connections` and finds a broken sync, that specific connection ID is saved to the shared context so the debugging agent can instantly call `get_connection` on it.

Yes, CrewAI supports stdio, SSE, and Streamable HTTP transports. When running in production, we recommend using the Streamable HTTP transport provided by Vinkius to keep your agents responsive.

Every tool execution, such as `get_source`, runs inside a secure, ephemeral V8 isolate sandbox on Vinkius. No database credentials or workspace secrets are ever cached, ensuring your pipeline configurations remain strictly confidential.

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