MCP Server Setup

Connect cloudlayer.io to your AI assistant so it can generate PDFs, images, and manage documents through natural language. The cloudlayer.io MCP server supports OAuth authentication — authorize once in your browser and your AI gets secure access to your account.

Server URL: https://mcp.cloudlayer.io/mcp


Claude Code

The fastest way to get started. Claude Code has built-in OAuth support — it handles authentication automatically.

Install

claude mcp add --transport http cloudlayer https://mcp.cloudlayer.io/mcp

Authenticate

  1. Run /mcp in Claude Code and select cloudlayer to authenticate
  2. Your browser opens to the cloudlayer.io consent page
  3. Sign in (or use your existing session) and click Authorize
  4. You’re connected — start using cloudlayer.io tools in conversation

Verify

Ask Claude Code something like:

  • “Check my cloudlayer account status”
  • “Generate a PDF from this HTML: <h1>Hello World</h1>
  • “What templates are available for invoices?”

Remove

claude mcp remove cloudlayer

Claude Desktop

  1. Open Settings → Connectors
  2. Click Add custom connector at the bottom
  3. Paste the server URL: https://mcp.cloudlayer.io/mcp
  4. Click Add

Claude Desktop handles OAuth automatically — it opens your browser to authorize when you first use a cloudlayer.io tool. Sign in and click Authorize.

Note: Remote MCP servers must be added via Settings → Connectors. The claude_desktop_config.json file is only for local servers.


Cursor

Option 1: Settings UI

  1. Open Settings: Cmd+, (Mac) or Ctrl+, (Windows)
  2. Navigate to Features → MCP
  3. Click + Add New MCP Server
  4. Enter name cloudlayer and URL https://mcp.cloudlayer.io/mcp

Option 2: Config File

Add to .cursor/mcp.json in your project root (or ~/.cursor/mcp.json for global):

{
  "cloudlayer": {
    "type": "http",
    "url": "https://mcp.cloudlayer.io/mcp"
  }
}

Note: Cursor has a limit of ~40 active tools across all MCP servers. cloudlayer.io registers 23 tools, so keep this in mind if you have other MCP servers configured.


Windsurf

Option 1: Settings UI

  1. Open Windsurf → Settings → Advanced Settings (or use Command Palette: Open Windsurf Settings Page)
  2. Scroll to the Cascade section
  3. Add a new MCP server

Option 2: Config File

Edit ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "cloudlayer": {
      "type": "http",
      "url": "https://mcp.cloudlayer.io/mcp"
    }
  }
}

Windsurf automatically reloads the config when you save.


VS Code + GitHub Copilot

Requires VS Code 1.99+ with GitHub Copilot.

  1. Open Settings: Cmd+, (Mac) or Ctrl+, (Windows)
  2. Search for MCP
  3. Click Add MCP Server
  4. Enter name cloudlayer and URL https://mcp.cloudlayer.io/mcp

Or add to .vscode/settings.json:

{
  "mcp": {
    "servers": {
      "cloudlayer": {
        "type": "http",
        "url": "https://mcp.cloudlayer.io/mcp"
      }
    }
  }
}

Cline

Option 1: Config UI

  1. Click the MCP Servers icon in Cline’s top navigation
  2. Select the Configure tab
  3. Click Configure MCP Servers
  4. Add the cloudlayer.io server

Option 2: Config File

Edit the Cline MCP settings file:

  • macOS: ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
  • Windows: %APPDATA%/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
  • Linux: ~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
{
  "mcpServers": {
    "cloudlayer": {
      "type": "http",
      "url": "https://mcp.cloudlayer.io/mcp"
    }
  }
}

Available Tools

Once connected, your AI assistant gets access to these tools:

Document Generation

  • html_to_pdf / html_to_image — Convert HTML to PDF or image
  • url_to_pdf / url_to_image — Capture a web page as PDF or image
  • template_to_pdf / template_to_image — Render a template with data
  • docx_to_pdf / docx_to_html — Convert DOCX files
  • pdf_to_docx — Convert PDF to DOCX
  • merge_pdfs — Merge multiple PDFs

Account & Resources

  • get_account — View usage and subscription info
  • list_jobs / get_job — Track conversion jobs
  • list_assets / get_asset — Browse generated documents
  • list_storage / get_storage / create_storage / delete_storage — Manage S3 storage
  • list_templates / get_template — Browse the template gallery
  • get_status — Check API status

Documentation

  • get_doc — Look up cloudlayer.io documentation by topic (e.g., get_doc "html-to-pdf")

Revoking Access

Each MCP authorization creates a dedicated API key. To revoke access:

  1. Go to app.cloudlayer.io/settings/api-keys
  2. Find the key created for your MCP connection (most recent)
  3. Click Revoke

The AI assistant will need to re-authorize next time it tries to use cloudlayer.io tools.


Troubleshooting

“Unauthorized” errors after connecting Your token may have expired or the API key was revoked. Remove and re-add the MCP server to trigger a fresh authorization.

Connection timeout Verify the server URL is exactly https://mcp.cloudlayer.io/mcp — including the /mcp path.

Tools not appearing Some clients need a restart after adding an MCP server. Try restarting your AI assistant.

Too many tools warning (Cursor) Cursor limits active tools to ~40. If you have other MCP servers, you may hit this limit. Consider removing unused servers.