3b879abd1f
## What Reorganizes the MCP (Model Context Protocol) server documentation to clearly distinguish between multiple Airbyte MCP servers and makes all MCP documentation discoverable through the sidebar. Requested by AJ Steers (@aaronsteers) in [this Devin session](https://app.devin.ai/sessions/7f61ccb7731f4009b19076fa2b5df36d). **Problem**: The existing MCP documentation only covered one remote MCP server (the Heroku-hosted "fast-coder" server), but there are actually four MCP servers: 1. The new PyAirbyte MCP (local STDIO server) - the recommended option 2. The PyAirbyte Fast-Coder MCP (remote Heroku server) - for rapid code generation 3. The Connector Builder MCP (in development) 4. The Embedded Operator MCP (existed but wasn't in the sidebar) ## How - **Renamed** `docs/ai-agents/pyairbyte-mcp/` → `docs/ai-agents/pyairbyte-fast-coder-mcp/` (the old remote server) - **Created** new `docs/ai-agents/pyairbyte-mcp/README.md` with documentation for the new local STDIO MCP server (copied from the docstring in `airbyte/mcp/__init__.py` in the PyAirbyte repo) - **Created** `docs/ai-agents/connector-builder-mcp/README.md` as a stub/"coming soon" page - **Updated** `docusaurus/sidebar-ai-agents.js` to: - Group all four MCP servers under a "MCP Servers" category - Add the previously hidden Embedded Operator MCP to the sidebar - **Updated** `docs/ai-agents/README.md` to describe all four MCP servers with clear distinctions - **Fixed** typo: "embedded source" → "embedded search" in the Fast-Coder MCP docs ## Review guide 1. **`docs/ai-agents/README.md`** - Verify the high-level descriptions of each MCP server are clear and accurate 2. **`docs/ai-agents/pyairbyte-mcp/README.md`** - Review the setup instructions for the new PyAirbyte MCP (local server). This content was copied from the PyAirbyte repo docstring - please verify it's complete and correct. 3. **`docs/ai-agents/pyairbyte-fast-coder-mcp/README.md`** - Verify the renamed "Fast-Coder" MCP docs are still accurate 4. **`docusaurus/sidebar-ai-agents.js`** - Check that the sidebar structure makes sense with all four MCP servers grouped together 5. **`docs/ai-agents/connector-builder-mcp/README.md`** - Confirm the stub page is appropriate for the in-development server **Key distinction to verify**: The new "PyAirbyte MCP" (local, recommended) vs "PyAirbyte Fast-Coder MCP" (remote, for code generation) are clearly differentiated in the docs. ## User Impact **Positive:** - Users can now discover all available Airbyte MCP servers in one place - The new PyAirbyte MCP (local STDIO server) is documented and positioned as the recommended option - The Embedded Operator MCP is now visible in the documentation sidebar - Clear guidance on which MCP server to use for different use cases **Potential confusion:** - Having two PyAirbyte-related MCP servers might initially confuse users, but the docs clearly explain the differences ## Can this PR be safely reverted and rolled back? - [x] YES 💚 This is purely documentation changes with no code or infrastructure changes. Rolling back would just restore the previous documentation structure. --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
2.7 KiB
products
| products |
|---|
| embedded |
PyAirbyte Fast-Coder MCP (Deprecated)
::warning The PyAirbyte Fast-Coder MCP has been deprecated and is no longer actively maintained. If you would like to see continued development on this tool, please let us know by adding feedback on the related GitHub Discussion. ::
The PyAirbyte Fast-Coder MCP is a remote MCP server that provides the ability for data engineers to generate a data pipeline in Python using a single prompt. It is currently designed to work within Cursor, with broader support coming in the near future.
To add the PyAirbyte MCP open Cursor and navigate to Settings > Tools & Integrations, and tap New MCP Sever. Add the following json snippet. This file tells Cursor which remote MCP servers to connect to and what credentials to pass along.
Paste the following into your mcp.json file:
{
"mcpServers": {
"pyairbyte-mcp": {
"url": "https://pyairbyte-mcp-7b7b8566f2ce.herokuapp.com/mcp",
"env": {
"OPENAI_API_KEY": "<your-openai-api-key>"
}
}
}
}
Make sure to replace <your-openai-api-key> with your actual key from the OpenAI platform.
Save the file. Cursor will automatically detect the MCP server and display pyairbyte-mcp as an available MCP tool with a green dot indicating that it has found the available tools.
Within your Cursor project, start a new chat. In the input box, type the following prompt:
create a data pipeline from source-faker to destination-snowflake
The MCP server will process your prompt and respond by generating all the necessary Python code to extract data from faker and load it into Snowflake. We suggest you prefix your source and destination with source- and destination- to ensure specificity when the MCP server performs a search on the Airbyte Connector registry. Connectors for sources and destinations may have the same name, but different configuration parameters.
In a few moments, your pipeline will be created, typically in a file called pyairbyte_pipeline.py. In addition, the MCP server will generate complete instructions on how to use the server and configure required parameters using a .env file that includes environment variables you’ll need to fill in.
Create a .env file and populate it with your source parameters and Snowflake connection details, per generated instructions. For example:
AIRBYTE_DESTINATION__SNOWFLAKE__HOST=your_account.snowflakecomputing.com
AIRBYTE_DESTINATION__SNOWFLAKE__USERNAME=your_user
AIRBYTE_DESTINATION__SNOWFLAKE__PASSWORD=your_password
AIRBYTE_DESTINATION__SNOWFLAKE__DATABASE=your_db
AIRBYTE_DESTINATION__SNOWFLAKE__SCHEMA=your_schema
AIRBYTE_DESTINATION__SNOWFLAKE__WAREHOUSE=your_warehouse