mcpField
P
plyo-mcp

plyo-mcp

Local
github.com/plyo-devCloud & Infra0Updated 8w ago

About plyo-mcp

plyo-mcp is an MCP server for people building projects with AI on Plyo. It lets an AI save versions, publish changes, restore checkpoints and back up project data.

Key features

  1. 01Create or link a Plyo project
  2. 02Save versioned checkpoints
  3. 03Publish and inspect build errors
  4. 04Create drafts and restore checkpoints
  5. 05Back up database and storage
  6. 06View project timeline and list

Use cases

  1. 01Save each completed piece of AI-built work
  2. 02Try changes in a draft before publishing
  3. 03Restore an earlier project version
  4. 04Back up data before migrations or deletions

MCP support

The MCP server exposes Plyo project and release operations as tools to MCP clients, including project management, checkpoints, publishing and backups.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"plyo-dev-plyo": {
"command": "npx",
"args": [
"-y",
"plyo-mcp"
],
"env": {
"PLYO_TOKEN": "<PLYO_TOKEN>"
}
}
}
}
Run commandnpx -y plyo-mcp
Environment variables to set
PLYO_TOKENSecretPlyo AI key (create in the dashboard: Settings > AI keys)

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmplyo-mcp0.4.3

Tools

10

Saved tool list · updated 2w ago

This tool takes no parameters.

Details

From the project README

plyo-mcp

MCP server for Plyo — 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.

Setup

Claude Code, one line:

claude mcp add plyo -e PLYO_TOKEN=plyo_xxx -- npx plyo-mcp

Any other MCP client:

{
  "mcpServers": {
    "plyo": {
      "command": "npx",
      "args": ["plyo-mcp"],
      "env": { "PLYO_TOKEN": "plyo_xxx" }
    }
  }
}

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 has the full picture; setup lives at plyo.dev/connect.html.

After setup, the user says: "I've added Plyo. Save this project there and keep saving as we go." That's the whole integration.

Tools

ToolWhat it does
create_projectCreate a Plyo project and link the current folder to it
link_projectLink the current folder to an existing project by slug
save_checkpointSave the current state to the project's timeline (pass intent: one sentence on what the user asked for; it powers timeline search)
publishPublish the latest checkpoint to the live URL; on failure returns a plain-English cause and a fix you can act on
get_build_errorLatest build status; if it failed, the translated error and fix guidance
start_draftSafe copy of the project to try changes without touching the live version
restoreReturn to an earlier checkpoint; never destructive, history is kept
get_timelineRecent checkpoints with what changed in each
backup_dataSnapshot the project's database and storage files before risky data changes
list_projectsThe user's projects with names, slugs and live URLs

Notes for agents

  • Call save_checkpoint after each completed piece of work, with a one-sentence intent.
  • Call backup_data before schema migrations, bulk updates or deletions.
  • Errors come back plain and actionable: publish and build failures include what went wrong and what to change.
  • 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).
  • A failed publish never takes a live site down.

MIT · plyo.dev · [email protected]

mcp-name: io.github.plyo-dev/plyo-mcp

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.