MCP server

public-it exposes an MCP (Model Context Protocol) server so AIs can create sites and publish artifacts directly, inside the conversation. Streamable HTTP transport with OAuth 2.1 or API-key authentication.

Connection

Endpoint	`https://public-it.com/mcp`
Transport	Streamable HTTP (spec 2025-03-26+)
Auth	Header `Authorization: Bearer pit_…` — create the key at Dashboard → API & MCP — or OAuth 2.1 (ChatGPT/Claude.ai: automatic, no key)

Setup per tool

Claude Code / Cowork plugindocs ↗

The public-it plugin bundles the remote MCP connector and guided setup/publishing skills. After it is approved in the community directory, install it from Claude Code or Cowork and run /public-it:setup. OAuth opens in the browser; never paste an API key into chat.

# After community-directory approval
/plugin install public-it@claude-plugins-community
/public-it:setup

# Local repository test
claude --plugin-dir ./public-it-skill

Claude Desktop / claude.ai (custom connector)docs ↗

URL: https://public-it.com/mcp
Authentication: OAuth 2.1 (browser)

ChatGPT plugin / Developer Modedocs ↗

After directory approval, find public-it under Plugins. For development, use Settings → Connectors → Advanced → Developer mode → Create and paste the endpoint URL above. No key is needed: ChatGPT self-registers and signs in via OAuth 2.1; you approve it once on a consent screen. Manage or revoke the connection later in Dashboard → API & MCP → Connected apps. Claude.ai's custom connector also works with just the URL (OAuth) if you skip the header.

https://public-it.com/mcp

Cursor / VS Code (mcp.json)docs ↗docs ↗

{
  "mcpServers": {
    "public-it": {
      "url": "https://public-it.com/mcp",
      "headers": { "Authorization": "Bearer YOUR_KEY" }
    }
  }
}

Gemini CLIdocs ↗

~/.gemini/settings.json

{
  "mcpServers": {
    "public-it": {
      "httpUrl": "https://public-it.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_KEY"
      }
    }
  }
}

Windsurfdocs ↗

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "public-it": {
      "serverUrl": "https://public-it.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_KEY"
      }
    }
  }
}

Cline (VS Code)docs ↗

cline_mcp_settings.json

{
  "mcpServers": {
    "public-it": {
      "type": "streamableHttp",
      "url": "https://public-it.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_KEY"
      }
    }
  }
}

JetBrains AI Assistantdocs ↗

Settings → Tools → AI Assistant → MCP → Add

{
  "mcpServers": {
    "public-it": {
      "url": "https://public-it.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_KEY"
      }
    }
  }
}

Zeddocs ↗

settings.json (bridge via mcp-remote)

{
  "context_servers": {
    "public-it": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "mcp-remote",
          "https://public-it.com/mcp",
          "--header",
          "Authorization: Bearer YOUR_KEY"
        ]
      }
    }
  }
}

OpenCodedocs ↗

opencode.json

{
  "mcp": {
    "public-it": {
      "type": "remote",
      "url": "https://public-it.com/mcp",
      "enabled": true,
      "headers": {
        "Authorization": "Bearer YOUR_KEY"
      }
    }
  }
}

Kirodocs ↗

.kiro/settings/mcp.json

{
  "mcpServers": {
    "public-it": {
      "url": "https://public-it.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_KEY"
      }
    }
  }
}

Traedocs ↗

.trae/mcp.json

{
  "mcpServers": {
    "public-it": {
      "url": "https://public-it.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_KEY"
      }
    }
  }
}

Replit (Agent)docs ↗

Settings → MCP Servers (UI)

+ Add MCP server → URL: https://public-it.com/mcp
Advanced → Header: Authorization = Bearer YOUR_KEY

ZCode (Z.ai)docs ↗

MCP Servers page (UI) — or import your Claude Code config

{
  "mcpServers": {
    "public-it": {
      "url": "https://public-it.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_KEY"
      }
    }
  }
}

GitHub Copilot (coding agent)docs ↗

Repo → Settings → Copilot → Coding agent → MCP

{
  "mcpServers": {
    "public-it": {
      "type": "http",
      "url": "https://public-it.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_KEY"
      }
    }
  }
}

Tools like Lovable, Base44, Bolt and Bubble are app builders that expose their ownMCP servers (you connect Claude/Cursor to them) — they can't consume external MCP servers like public-it yet.

OAuth and revocation

Browser-based clients use Authorization Code + PKCE and refresh tokens. Authorization lets the app view, create, publish, roll back and delete your sites. Revoke a client at any time under Dashboard → API & MCP → Connected apps; access stops immediately.

Available tools

Tool	Description	Parameters
`list_sites`	List all sites of the authenticated user, with public URLs and status.	—
`create_site`	Create a new site. The subdomain becomes the public address. Use publish_html afterwards.	`name` · Human-friendly site name `subdomain` · 3-63 chars, lowercase letters, numbers and hyphens `useWorkspaceSubdomain`? · Optional opt-in to use the suggested site-workspace address; false by default
`publish_files`	Publish a multi-page site: several files (HTML/CSS/JS/SVG) with folders, up to ~5MB per call. Text by default, base64 per file for small binaries.	`files` · Up to 200 of { path, content, base64? } — e.g. path 'blog/post.html' `siteId`? · Site id (or use subdomain) `subdomain`? · Alternative to siteId `entryFile`? · File served at '/' (default index.html)
`publish_html`	Publish a complete HTML document as the new live version of a site. Returns the public URL. Prefer self-contained HTML (inline CSS/JS).	`html` · Complete HTML document `siteId`? · Site id (or use subdomain) `subdomain`? · Alternative to siteId
`get_site`	Get details of one site (status, live version, URL, storage).	`siteId` · Site id
`list_versions`	List the publication history of a site (for rollback).	`siteId` · Site id
`rollback_site`	Restore an archived version of a site (paid plans).	`siteId` · Site id `publicationId` · Archived version id
`delete_site`	Permanently delete a site and its files. Confirm with the user first.	`siteId` · Site id
`get_usage`	Get the user's plan, site count and storage usage.	—

Typical flow

A common conversation between a user and an AI connected to public-it:

You:  "Finish those last details on the presentation page and publish it on public-it"
AI:   … polishes the artifact (copy, spacing, colors) …
      → create_site(name: "Launch Deck", subdomain: "launch-deck")
      → publish_html(subdomain: "launch-deck", html: "<final version>")
AI:   "Done — details wrapped up and live at https://launch-deck.public-it.com"

Every publish_html puts a new version live — the history is available for rollback on paid plans (list_versions + rollback_site).

Errors

Without the authorization header the server responds 401. Business errors (quota exceeded, subdomain taken) come back as tool results with isError: true and a message explaining what to do:

quota_exceeded: Your Free plan allows up to 1 site(s) — upgrade to publish more.