Linkly MCP Server

The Linkly MCP Server lets you connect AI assistants to your Linkly account using the Model Context Protocol. Once connected, you can create and manage short links through natural conversation.

The Model Context Protocol (MCP) is an open standard that allows AI assistants to securely connect to external tools and data sources. Instead of copying and pasting between apps, you can ask your AI assistant to perform actions directly.

The Linkly MCP Server works with:

• Claude Desktop
• ChatGPT Desktop
• Other MCP-compatible clients (Cursor, Windsurf, etc.)

Once connected, you can ask your AI assistant to:

• Create short links - "Create a short link for https://example.com"
• Track performance - "How many clicks did my links get this week?"
• Manage links - "Update the link called 'promo' with a new destination"
• View analytics - "Show me clicks by country for the last 30 days"
• Search links - "Find all links related to the product launch"
• Manage domains - "List my custom domains"
• Set up webhooks - "Subscribe https://my-site.com/webhook to receive click events"

The Linkly MCP Server is available in two ways:

Use our hosted MCP server - no installation required:

https://mcp.linklyhq.com

Install and run locally using npx:

npx -y linkly-mcp-server

Or install globally:

npm install -g linkly-mcp-server

View the package on npm or GitHub.

1. Log in to your Linkly dashboard
2. Go to Settings → API Keys
3. Copy your API Key and Workspace ID

Open your Claude Desktop config file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

Add the Linkly MCP server:

{
  "mcpServers": {
    "linkly": {
      "command": "npx",
      "args": ["-y", "linkly-mcp-server"],
      "env": {
        "LINKLY_API_KEY": "your-api-key",
        "LINKLY_WORKSPACE_ID": "your-workspace-id"
      }
    }
  }
}

Open your ChatGPT config file:

• macOS: ~/Library/Application Support/ChatGPT/mcp_servers.json
• Windows: %APPDATA%\ChatGPT\mcp_servers.json

Add the Linkly MCP server:

Using npx:

{
  "servers": {
    "linkly": {
      "command": "npx",
      "args": ["-y", "linkly-mcp-server"],
      "env": {
        "LINKLY_API_KEY": "your-api-key"
      }
    }
  }
}

Using hosted server:

{
  "servers": {
    "linkly": {
      "type": "url",
      "url": "https://mcp.linklyhq.com",
      "env": {
        "LINKLY_API_KEY": "your-api-key"
      }
    }
  }
}

When creating links, you can specify:

• Basic: url, name, note, domain, slug, enabled
• UTM Parameters: utm_source, utm_medium, utm_campaign, utm_term, utm_content
• Open Graph: og_title, og_description, og_image
• Tracking: fb_pixel_id, ga4_tag_id, gtm_id
• Advanced: cloaking, forward_params, block_bots, hide_referrer
• Expiry: expiry_datetime, expiry_destination

• Check that your API key and Workspace ID are correct
• Ensure you have Node.js installed (v18 or later)
• Try running npx linkly-mcp-server in a terminal to see any errors

• Verify your API key in the Linkly dashboard at Settings → API Keys
• Make sure there are no extra spaces in your credentials
• Try regenerating your API key

• Restart your AI assistant after saving the configuration
• Check that the JSON syntax in your config file is valid
• Verify the MCP server is running (check for the tools icon in your assistant)

• Confirm that the command path is correct
• If using the hosted server, check your internet connection
• Verify the MCP server runs manually from the terminal

• Claude Desktop Integration
• ChatGPT Integration
• Linkly API Documentation
• Webhooks
• MCP Server on npm
• Model Context Protocol