generate_pyairbyte_pipelineLABSCO SUMMARY
One tool, and the connector names do the work.
The whole interface is a single call taking two official Airbyte connector names, which keeps the failure mode obvious: get the source- or destination- prefix right and you get working code, get it wrong and you get the wrong connector. Asking for dataframe as the destination is the fastest route from a source system to something you can actually poke at in Pandas.
What it is
An MCP server you run locally that generates PyAirbyte pipeline code. You name an Airbyte source connector and a destination connector; it writes the Python, the setup steps and the credential scaffolding, using connector documentation and OpenAI for context. Anything in the Airbyte Connector Registry is fair game.
What you get
- Complete PyAirbyte pipeline code from a source connector name and a destination connector name —
generate_pyairbyte_pipeline - Setup and installation instructions alongside the script, plus environment-variable templates for the credentials the connectors need
dataframeas a destination when the endpoint is Pandas analysis rather than a warehouse — the generated code hands you frames instead of a load step
Requirements
Python 3.10, 3.11 or 3.12 and your own OpenAI API key. The hosted server the README points to is gone, so you run it yourself: pip install -r requirements.txt, then start main.py with OPENAI_API_KEY set — it serves Streamable HTTP on http://localhost:8000/mcp, which is the URL your client takes. An optional OpenAI vector store ID enables file search over uploaded PyAirbyte docs.
Setup effort
Build from source — git clone https://github.com/quintonwall/airbyte-labs-pyairbyte-mcp && cd airbyte-labs-pyairbyte-mcp
USE CASES
01
Standing up a warehouse load without writing the boilerplate
Name the source and destination connectors and get a complete pipeline script plus the environment variables it expects.
02
Pulling a source into Pandas for a one-off look
Ask for the pipeline with dataframe as the destination, so the generated code lands the data in frames instead of a warehouse.
03
Evaluating a connector you have not used before
Generate the pipeline for it and read the setup instructions and credential template to see what the integration will actually require.
1 tool
Listed in project docs. Your client may show a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool named in the project's documentation.
Requires
- Python 3.10, 3.11 or 3.12 with pip
- OPENAI_API_KEY in the server's environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/quintonwall/airbyte-labs-pyairbyte-mcp && cd airbyte-labs-pyairbyte-mcp
pip install -r requirements.txt
OPENAI_API_KEY=<YOUR_OPENAI_API_KEY> python main.pyThe server listens for Streamable HTTP on http://localhost:8000/mcp. Set PORT to use a different port.
MCP Clients
Any MCP client — Local
ANY MCP CLIENT — LOCAL · JSON
{
"mcpServers": {
"pyairbyte-mcp": {
"url": "http://localhost:8000/mcp"
}
}
}
