# snowfakery-mcp

An MCP server that lets your AI assistant write, check and run Snowfakery recipes, and build CumulusCI mappings along the way.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 5
- Author: composable-delivery
- License: Apache-2.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/composable-delivery/snowfakery-mcp
- Updated: 2026-09-30
- HTML: https://affpapa.org/en/nevibecode/mcp/snowfakery-mcp

## What it 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.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add snowfakery-mcp -- uvx snowfakery-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from snowfakery-mcp <command>

### Codex

**Platform CLI**
```bash
codex mcp add snowfakery-mcp -- uvx snowfakery-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from snowfakery-mcp <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "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>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "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>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add snowfakery-mcp uvx snowfakery-mcp
```
uvx runs the command named after the package; if the README names another one, use uvx --from snowfakery-mcp <command>

## When to use it
- 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
- Show me an example Snowfakery recipe
- Help me write a recipe that generates 100 Salesforce accounts
- Validate `accounts.yml` and explain the errors

## Similar
- [test-data-management](https://affpapa.org/en/nevibecode/skills/test-data-management.md) — skill · 1300 installs
- [adding-dbt-unit-test](https://affpapa.org/en/nevibecode/skills/adding-dbt-unit-test.md) — skill · 1100 installs
- [platform-data-manage](https://affpapa.org/en/nevibecode/skills/platform-data-manage.md) — skill · 6100 installs
- [metabase-semantic-checker](https://affpapa.org/en/nevibecode/skills/metabase-semantic-checker.md) — skill · 429 installs
- [turbo-pipelines](https://affpapa.org/en/nevibecode/skills/turbo-pipelines.md) — skill · 3600 installs
- [platform-apex-test-generate](https://affpapa.org/en/nevibecode/skills/platform-apex-test-generate.md) — skill · 7100 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md