{
  "markdown": "# Snowfakery MCP Server\n\n[![CI](https://github.com/composable-delivery/snowfakery-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/composable-delivery/snowfakery-mcp/actions/workflows/ci.yml)\n[![PyPI](https://img.shields.io/pypi/v/snowfakery-mcp.svg)](https://pypi.org/project/snowfakery-mcp/)\n[![License](https://img.shields.io/github/license/composable-delivery/snowfakery-mcp.svg)](LICENSE-MIT)\n\n**Power up your AI workflows with Snowfakery data generation** — Use Claude, ChatGPT, and other AI assistants to author, debug, and run data recipes through the [Model Context Protocol](https://modelcontextprotocol.io/).\n\n## MCP Registry\n\nmcp-name: io.github.composable-delivery/snowfakery-mcp\n\n## What is this?\n\n[Snowfakery](https://github.com/SFDO-Tooling/Snowfakery) is a YAML-based tool for programmatically generating test data. This MCP server connects Snowfakery to AI assistants, letting you:\n\n- **Draft recipes** with AI assistance backed by real Snowfakery docs and examples\n- **Validate recipes** before running them with detailed error feedback\n- **Execute recipes** and iterate on results interactively\n- **Debug issues** with static analysis and recipe inspection\n- **Generate Salesforce mappings** for CumulusCI workflows\n\nPerfect for teams that need realistic test data—from Salesforce admins to developers building data pipelines.\n\n## Quick Start\n\n### Install `uv`\n\nWe recommend using `uv` for installs and for running from source.\n\n- Install `uv` (macOS/Linux):\n\n  ```bash\n  curl -LsSf https://astral.sh/uv/install.sh | sh\n  ```\n\n- Install `uv` (Windows PowerShell):\n\n  ```powershell\n  powershell -ExecutionPolicy ByPass -c \"irm https://astral.sh/uv/install.ps1 | iex\"\n  ```\n\nSee the official `uv` install docs: <https://docs.astral.sh/uv/getting-started/installation/>\n\n### Claude Desktop (recommended)\n\nFor Claude Desktop, prefer using the `.mcpb` bundle from Releases:\n\n- Download the latest `.mcpb` from <https://github.com/composable-delivery/snowfakery-mcp/releases>\n- Add the bundle in Claude Desktop as an MCP server bundle\n\nThis bundle includes the pinned runtime metadata (`uv.lock`, `manifest.json`) and is the easiest way to get a reproducible setup.\n\n### Install & Run (CLI)\n\n```bash\n# Recommended: isolated install\nuv tool install snowfakery-mcp\n\n# Then run the server\nsnowfakery-mcp\n```\n\nOr from source:\n\n```bash\ngit clone https://github.com/composable-delivery/snowfakery-mcp.git\ncd snowfakery-mcp\nuv sync\nuv run snowfakery-mcp\n```\n\n### Connect to Claude (Desktop)\n\nAdd to your Claude Desktop `claude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"snowfakery-mcp\": {\n      \"command\": \"snowfakery-mcp\"\n    }\n  }\n}\n```\n\nThen ask Claude:\n> \"Show me an example Snowfakery recipe\" or \"Help me write a recipe to generate 100 Salesforce accounts\"\n\n## Features\n\n**Resources** — Access docs, examples, and schemas:\n\n- Snowfakery documentation and recipe examples\n- JSON schema for recipe validation\n- Run outputs and artifacts\n\n**Tools** — Interact with recipes:\n\n- Validate & analyze recipes (catch errors early)\n- Run recipes and capture output\n- List & retrieve example recipes\n- Generate CumulusCI mapping files\n\n## Learn More\n\n- **[MCP_SERVER_SPEC.md](MCP_SERVER_SPEC.md)** — detailed design and tool catalog\n- **[Snowfakery docs](https://snowfakery.readthedocs.io/)** — recipe language reference\n- **[Contributing](CONTRIBUTING.md)** — how to contribute\n\n## Community\n\nWe want this to be welcoming at any level. Questions, ideas, and contributions are always welcome!\n\n- **Questions & ideas?** Open a [GitHub Discussion](https://github.com/composable-delivery/snowfakery-mcp/discussions)\n- **Found a bug?** [Open an Issue](https://github.com/composable-delivery/snowfakery-mcp/issues) with a minimal recipe\n- **Want to contribute?** See [CONTRIBUTING.md](CONTRIBUTING.md)\n- **Security concern?** See [SECURITY.md](SECURITY.md)\n\n## Development\n\n```bash\n# Install dev dependencies\nuv sync --all-groups\n\n# Run tests\nuv run pytest\n\n# Type check\nuv run mypy snowfakery_mcp\n\n# Lint & format\nuv run ruff check snowfakery_mcp tests scripts evals\nuv run ruff format snowfakery_mcp tests scripts evals\n```\n\n### Evals (Agentic Testing)\n\nThis repo includes `inspect-ai` tasks for testing the MCP server with AI models:\n\n```bash\n# Install eval dependencies\nuv sync --group evals\n\n# Run evaluation\nuv run inspect eval evals/inspect_tasks.py@snowfakery_mcp_agentic --model openai/gpt-4o-mini\n```\n\nSee [evals/](evals/) for more examples and troubleshooting.\n\n## Notes\n\n- The repo includes the upstream Snowfakery repo as a git submodule (`Snowfakery/`) for development\n- When running from source, use `uv run ...` to ensure the pinned environment\n- PyPI installs use bundled docs/examples (no submodule required)\n\n## Releases\n\nSee [GitHub Releases](https://github.com/composable-delivery/snowfakery-mcp/releases) for sdist, wheel, and `.mcpb` bundles (recommended for Claude Desktop).\n",
  "bytes": 4919,
  "sha": "fda3290a3c96652ef441b03091b3e3d251108c9c02d7bd7c234c3da8fd7630b9",
  "repo_slug": "composable-delivery/snowfakery-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_composable_delivery_snowfakery_bf55da91/readme"
}