MCP Integration

SnipperApp 3 includes a built-in Model Context Protocol (MCP) server, allowing AI assistants to directly read, search, create, and manage your code snippets. This makes your snippet library an active part of your AI-assisted development workflow.

What Is MCP?

The Model Context Protocol is an open standard that enables AI applications to interact with external tools and data sources. When you connect SnipperApp 3 as an MCP server, your AI assistant can:

• Search your snippet library by keyword, language, folder, or tag.
• Read the full content of any snippet.
• Create new snippets from AI-generated code.
• Update existing snippets.
• Manage folders, tags, and attachments.

This means you can ask your AI assistant things like "find my Python database connection snippet" or "save this code as a new snippet in my Utilities folder" -- and it interacts directly with SnipperApp.

Setup

Claude Code

Setup is a single command. Run this in your terminal:

claude mcp add snipper /Applications/SnipperApp\ 3.app/Contents/MacOS/snipper-mcp

That's it. Claude Code will now have access to your SnipperApp snippets.

Claude Desktop

Add the following to your Claude Desktop MCP configuration file (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "snipper": {
      "command": "/Applications/SnipperApp 3.app/Contents/MacOS/snipper-mcp",
      "args": []
    }
  }
}

Restart Claude Desktop after saving the configuration. The SnipperApp tools will appear in Claude's tool list.

Cursor

Add the MCP server configuration in Cursor's settings:

1. Open Cursor Settings.
2. Navigate to the MCP or Tools section.
3. Add a new MCP server with the following configuration:

{
  "mcpServers": {
    "snipper": {
      "command": "/Applications/SnipperApp 3.app/Contents/MacOS/snipper-mcp",
      "args": []
    }
  }
}

4. Save and restart Cursor.

Other MCP-Compatible Clients

Any application that supports the Model Context Protocol can connect to SnipperApp 3 using the same binary path:

/Applications/SnipperApp 3.app/Contents/MacOS/snipper-mcp

No arguments are required. The MCP server communicates via standard input/output (stdio transport).

Available MCP Tools

Once connected, the following tools are available to AI assistants:

Snippet Management

Organization

Attachments

Usage Examples

Here are examples of how you might interact with your snippets through an AI assistant:

Searching for Snippets

"Find all my Python snippets related to database connections."

The AI assistant uses search_snippets with keyword "database connection" and language filter "Python" to find matching snippets.

Saving AI-Generated Code

"Save this function as a new snippet called 'Retry with Backoff' in my Utilities folder, tagged with 'python' and 'error-handling'."

The AI assistant uses create_snippet to save the code with the specified title, folder, and tags.

Retrieving a Snippet

"Get me my Docker Compose template for a PostgreSQL setup."

The AI assistant uses search_snippets to find the snippet, then get_snippet to retrieve its full content.

Updating a Snippet

"Update my API auth middleware snippet to use the new token format."

The AI assistant uses search_snippets to find the snippet, get_snippet to read the current content, modifies it, and then uses update_snippet to save the changes.

Requirements

• SnipperApp 3 must be installed at the standard path (/Applications/SnipperApp 3.app).
• The MCP binary is bundled with the app -- no additional installation is needed.
• The MCP server reads from and writes to the same database as the main app. Changes made through MCP appear immediately in the app and vice versa.

Security

• The MCP server runs locally on your Mac. No data is sent to external servers by the MCP server itself.
• The server operates with the same permissions as the calling application.
• All snippet data stays within your local machine and iCloud account.

Troubleshooting

Related

• Keyboard Shortcuts -- Quick reference for all shortcuts.
• Workspaces -- MCP operates within the active workspace context.