snowfakery-mcp — Claude Code MCP server: Snowfakery recipes
An MCP server that lets your AI assistant write, check and run Snowfakery recipes, and build CumulusCI mappings along the way.
claude mcp add snowfakery-mcp -- uvx snowfakery-mcpWhat snowfakery-mcp does
Snowfakery generates test data from YAML recipes. This server hands the assistant the docs, the example recipes and the validation schema, so a draft starts from working examples instead of a blank file. You can then check the recipe before running it and read a breakdown of what went wrong.
Resources cover documentation, sample recipes, the JSON schema and run artifacts. Tools validate and analyse recipes, execute them and capture the output, list the bundled examples, and produce CumulusCI mapping files.
Install runs through uv. No uv on the machine means uvx snowfakery-mcp simply will not start, so sort that out first. Working from source pulls the upstream Snowfakery repo in as a git submodule; a PyPI install ships its own docs and examples instead.
What it helps with
- draft a Snowfakery recipe from real examples
- catch recipe errors before a run
- execute a recipe and inspect the generated records
- trace a YAML problem through static analysis
- produce a CumulusCI mapping file
Example prompts for the agent
- Show me an example Snowfakery recipe
- Help me write a recipe that generates 100 Salesforce accounts
- Validate
accounts.ymland explain the errors
How to install snowfakery-mcp
Platform CLI
claude mcp add snowfakery-mcp -- uvx snowfakery-mcpuvx runs the command named after the package; if the README names another one, use uvx --from snowfakery-mcp <command>
Platform CLI
codex mcp add snowfakery-mcp -- uvx snowfakery-mcpuvx runs the command named after the package; if the README names another one, use uvx --from snowfakery-mcp <command>
Config file
{
"mcpServers": {
"snowfakery-mcp": {
"command": "uvx",
"args": [
"snowfakery-mcp"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from snowfakery-mcp <command>
Config file
{
"servers": {
"snowfakery-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"snowfakery-mcp"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from snowfakery-mcp <command>
Platform CLI
gemini mcp add snowfakery-mcp uvx snowfakery-mcpuvx runs the command named after the package; if the README names another one, use uvx --from snowfakery-mcp <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about snowfakery-mcp
How do I install snowfakery-mcp in Claude Code?
Run claude mcp add snowfakery-mcp -- uvx snowfakery-mcp. You need uv installed first.
What does snowfakery-mcp do?
It gives the assistant Snowfakery docs and examples so it can author recipes, validate them, run them and generate CumulusCI mappings.
What does snowfakery-mcp need to run?
A working uv install, since the server starts via uvx. PyPI installs bundle the docs and examples.
