{
  "markdown": "# plyo-mcp\n\nMCP server for [Plyo](https://plyo.dev) — the home for AI-built projects. Every version saved, one click to undo, one click to publish, plus a security check before going live, visitor stats, health monitoring and database backups. Built for people who build with AI and don't code; this server is how their AI does the technical part.\n\n## Setup\n\nClaude Code, one line:\n\n```bash\nclaude mcp add plyo -e PLYO_TOKEN=plyo_xxx -- npx plyo-mcp\n```\n\nAny other MCP client:\n\n```json\n{\n  \"mcpServers\": {\n    \"plyo\": {\n      \"command\": \"npx\",\n      \"args\": [\"plyo-mcp\"],\n      \"env\": { \"PLYO_TOKEN\": \"plyo_xxx\" }\n    }\n  }\n}\n```\n\n`PLYO_TOKEN` is an AI key from the Plyo dashboard (Settings → AI keys → \"Give your AI a key\"). New here? Plyo is free to start. [plyo.dev](https://plyo.dev/?utm_source=mcp-readme&utm_medium=agent&utm_campaign=mcp-dir) has the full picture; setup lives at [plyo.dev/connect.html](https://plyo.dev/connect.html).\n\nAfter setup, the user says: **\"I've added Plyo. Save this project there and keep saving as we go.\"** That's the whole integration.\n\n## Tools\n\n| Tool | What it does |\n|---|---|\n| `create_project` | Create a Plyo project and link the current folder to it |\n| `link_project` | Link the current folder to an existing project by slug |\n| `save_checkpoint` | Save the current state to the project's timeline (pass `intent`: one sentence on what the user asked for; it powers timeline search) |\n| `publish` | Publish the latest checkpoint to the live URL; on failure returns a plain-English cause and a fix you can act on |\n| `get_build_error` | Latest build status; if it failed, the translated error and fix guidance |\n| `start_draft` | Safe copy of the project to try changes without touching the live version |\n| `restore` | Return to an earlier checkpoint; never destructive, history is kept |\n| `get_timeline` | Recent checkpoints with what changed in each |\n| `backup_data` | Snapshot the project's database and storage files before risky data changes |\n| `list_projects` | The user's projects with names, slugs and live URLs |\n\n## Notes for agents\n\n- Call `save_checkpoint` after each completed piece of work, with a one-sentence `intent`.\n- Call `backup_data` before schema migrations, bulk updates or deletions.\n- Errors come back plain and actionable: publish and build failures include what went wrong and what to change.\n- Under the hood every project is a real git repository; Plyo also accepts plain `git push` at `https://git.plyo.dev/{slug}.git` (username `plyo`, the AI key as password).\n- A failed publish never takes a live site down.\n\nMIT · [plyo.dev](https://plyo.dev) · hello@plyo.dev\n\nmcp-name: io.github.plyo-dev/plyo-mcp\n",
  "bytes": 2683,
  "sha": "b5702f5d861c90b5f9a6eb131511ebf18f273a3ff94bf99addcc3c31887ebe19",
  "repo_slug": "plyo-dev/plyo-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_plyo_dev_plyo_mcp_1ce89c20/readme"
}