PyAirbyte

- Generates PyAirbyte pipeline codebased on user instructions and connector documentation.
- Uses OpenAI and file searchto provide context-aware code and instructions.
- Available as a remote MCP serverfor Cursor.

The easiest way to get started is using our hosted MCP server. Add this to your Cursor MCP configuration file (.cursor/mcp.json):

{ "mcpServers": { "pyairbyte-mcp": { "url": "https://pyairbyte-mcp-7b7b8566f2ce.herokuapp.com/mcp", "env": { "OPENAI_API_KEY": "your-openai-api-key-here" } } } }

- API keys are provided via MCP environment variables in the configuration
- This ensures secure API key handling through the MCP protocol
- Cursor is currently the only client that appears to support passing in ENV for remote servers. We will add Cline support as soon as available.

Once configured, you can use the MCP server in your AI assistant by asking it to generate PyAirbyte pipelines.

2. Generate Pipelines with Natural Language

Simply ask Cline to generate a PyAirbyte pipeline! Here are example prompts:

Generate a PyAirbyte pipeline from source-postgres to destination-snowflake

Create a pipeline to move data from source-github to dataframe

Build a PyAirbyte script for source-stripe to destination-bigquery

Generate a data pipeline from source-salesforce to destination-postgres

Create a pipeline that reads from source-github to a dataframe, and then visualize the results using Streamlit

Help me set up a data pipeline from source-salesforce to destination-postgres

- Sources: Any Airbyte source connector (e.g.,source-postgres,source-github,source-stripe,source-mysql,source-salesforce)
- Destinations: Any Airbyte destination connector (e.g.,destination-snowflake,destination-bigquery,destination-postgres) ORdataframefor Pandas analysis

- Use "dataframe"as destination if you want to analyze data in Python/Pandas
- Be specificabout your source and destination names (use official Airbyte connector names and use source- or destination- to specify)
- Ask follow-up questionsif you need help with specific configuration or setup

The tool will automatically use your OpenAI API key (configured in the MCP settings) to generate enhanced, well-documented pipeline code with best practices and detailed setup instructions!

Just start by asking Cline to generate a pipeline for your specific use case! 🎯

Generates a complete PyAirbyte pipeline with setup instructions.

- source_name: The official Airbyte source connector name (e.g., 'source-postgres', 'source-github')
- destination_name: The official Airbyte destination connector name (e.g., 'destination-postgres', 'destination-snowflake') OR 'dataframe' to output to Pandas DataFrames

- Complete Python pipeline code
- Setup and installation instructions
- Environment variable templates
- Best practices and usage guidelines

MCP Persistence: your AI Agent now creates and manages databases on its own

MCP servers for Deephaven to orchestrate data workers and power documentation Q&A with LLMs, enabling AI-driven data workflows.

Build robust data workflows, integrations, and analytics on a single intuitive platform.

An MCP server that provides tools to interact with Powerdrill datasets, enabling smart AI data analysis and insights.

Apify-hosted MCP server for Airtable with 15 tools. Full CRUD for records, tables, fields, search, and schema inspection. No local setup needed.

Interact with AskTable SaaS or local deployments to query data sources using natural language.

Production-grade MCP server for Databricks: SQL Warehouses, Jobs API, multi-workspace support.

Visual no-code generator that turns any database into multiple scoped MCP servers — one per access group, with PII masking and fail-closed query scoping built in.

A Model Context Protocol server for CData Sync, enabling data replication and transformation.