Snowfakery

Provides an MCP server that connects Snowfakery data generation to AI assistants for drafting, validating, and executing recipes.

python

3

GitHub Stars

python

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "composable-delivery-snowfakery-mcp": {
      "command": "snowfakery-mcp",
      "args": []
    }
  }
}

Snowfakery MCP Server connects Snowfakery, a YAML-based data generation tool, to AI assistants so you can draft, validate, run, and debug data recipes interactively. It enables generation of realistic test data for workflows and pipelines while leveraging AI to assist with recipe creation and inspection.

How to use

You will use an MCP client to interact with the Snowfakery MCP Server. Start by ensuring the MCP server is available through your Claude Desktop or another MCP client. You can draft recipes with AI assistance, validate them to catch errors early, run recipes to generate outputs, and inspect results to iterate quickly. Use the server to generate Salesforce mappings for CumulusCI workflows or to explore example recipes and schemas.

How to install

Prerequisites you need before installing include a compatible environment for the lightweight CLI tool and a way to install the MCP server runtime.

Install the uv runner for isolated environments and reproducible setups.

Then install and run the Snowfakery MCP Server using the following steps.

# Recommended: isolated install
uv tool install snowfakery-mcp

# Then run the server
snowfakery-mcp

# Or run from source
git clone https://github.com/composable-delivery/snowfakery-mcp.git
cd snowfakery-mcp
uv sync
uv run snowfakery-mcp

Additional notes

To connect with Claude Desktop, add an MCP server entry that runs the Snowfakery MCP Server. The example configuration shown is a typical local setup used by Claude Desktop.

Configuration and usage details

Key capabilities include drafting and validating recipes with AI assistance, executing recipes and inspecting outputs, and retrieving example recipes or generating mapping files for CumulusCI. This makes it easy to iterate on data generation workflows and debug issues with static analysis and recipe inspection.

Troubleshooting

If you encounter issues, verify the MCP server is running, ensure Claude Desktop can reach the local command, and check for any environment requirements or pinned runtime metadata. Use the evaluation and debugging tools to inspect recipe validation and execution results.

Security and maintenance

Maintain up-to-date runtimes and keep your recipes secure by validating inputs and reviewing generated outputs before use in production-like environments.

Available tools

Validate & analyze recipes

Check recipe syntax and semantics to catch errors early, providing detailed feedback on issues detected.

Run recipes

Execute a recipe to generate data and capture outputs for inspection and iteration.

List & retrieve example recipes

Access a library of example recipes to accelerate learning and experimentation.

Generate CumulusCI mappings

Create Salesforce mappings for CumulusCI workflows based on your recipes and outputs.