Skip to main content

Prerequisites

Before you begin, make sure you have:
  1. A paid Superlines plan — the MCP server is included on every plan (Starter, Pro, Growth, Enterprise, and the Agency plans)
  2. Either an API key (format: sl_live_...) or an OAuth sign-in:
    • API keys are available on Growth and Enterprise (and Agency Growth and Agency Enterprise), from Organization Settings
    • OAuth works on every plan, including Starter and Pro — use it with Claude.ai or any MCP client that supports OAuth sign-in, pointing it at https://mcpsse.superlines.io
  3. An MCP-compatible client installed
On Starter and Pro, API keys are not available, so the API-key and npx methods below won’t work. Connect with OAuth instead.

Connection methods

SSE connection URL:
Replace YOUR_API_KEY with your actual API key.

Choose your platform

Claude.ai

OAuth — no API key needed

Claude Desktop

SSE or local npx

Claude Code

CLI — one command setup

Cursor

SSE or local npx

Cursor Cloud

SSE — remote agents

Windsurf

SSE or local npx

Lovable

SSE via Settings UI

ChatGPT

Connector URL

n8n

MCP Client node

VS Code

SSE or local npx

Claude.ai

Method: OAuth — no API key needed. You authorize access with your Superlines account.
1

Open Claude.ai settings

Go to claude.ai → Settings → Connectors → Add custom connector.
2

Enter the server details

  • Name: Superlines
  • URL: https://mcpsse.superlines.io
  • Open Advanced settings and set OAuth Client ID to anthropic-claude
  • Leave OAuth Client Secret blank
  • Click Add
3

Authorize access

Claude will redirect you to the Superlines authorization page. Sign in with your Superlines account, review the requested permissions, select which brands to share, and click Authorize Access.
4

Start using Superlines

Back in Claude, start a new conversation and try: “List my Superlines brands”
OAuth connections are scoped to the brands you select during authorization. You can revoke access at any time from your Superlines account settings.

Claude Desktop

Method: SSE (recommended) or local npx. Both use the claude_desktop_config.json config file.
1

Open Claude Desktop settings

Go to Settings → Developer → Edit Config to open:
On Windows:
2

Add the Superlines server

3

Restart Claude Desktop

Save the file and fully restart the app for changes to take effect.

Claude Code

Method: CLI — add the server directly from your terminal with one command.
1

Add the Superlines server

Run one of these commands in your terminal:
2

Verify the connection

You should see superlines in the list of connected servers.
3

Start using Superlines

In your Claude Code session, try: “List my Superlines brands”
Use the --scope flag to control where the configuration is stored:
  • --scope local (default) — private to you, this project only
  • --scope project — shared via .mcp.json, checked into git
  • --scope user — available across all your projects

Cursor

Method: SSE (recommended) or local npx via .cursor/mcp.json.
1

Open MCP settings

Go to Cursor Settings → Tools & MCP → Add new MCP server, or create/edit the .cursor/mcp.json file in your project root.
2

Add the Superlines server

3

Restart Cursor

Restart Cursor for the changes to take effect. You should see the Superlines server listed under Tools & MCP in settings.

Cursor Cloud

Method: SSE only — cloud agents run in remote VMs, so local npx is not available.
Since Cursor Cloud agents run in a remote environment, only the SSE (URL-based) connection method works.
1

Add the Superlines server

Add the following to your .cursor/mcp.json file in your project root:
2

Commit the config

Commit the .cursor/mcp.json file to your repository so it’s available in the cloud environment.
3

Verify in cloud session

When using a Cursor Cloud agent, the Superlines tools will be available automatically. Try asking: “List my Superlines brands”
Local npx transport does not work with Cursor Cloud agents. Always use the SSE method for cloud environments.

Windsurf

Method: SSE URL or local npx via mcp_config.json. You can also browse the built-in MCP Marketplace.
1

Open MCP configuration

In Windsurf, click the Plugins icon in the sidebar → Manage plugins → View raw config, or edit the file directly:
2

Add the Superlines server

3

Refresh Windsurf

Save the file and restart Windsurf, or refresh the MCP plugins from the sidebar.
Windsurf supports environment variable interpolation in MCP configs. You can use ${env:SUPERLINES_API_KEY} in the serverUrl to reference environment variables instead of hardcoding your key.

Lovable

Method: SSE URL via Settings UI. Custom MCP servers are available on all paid Lovable plans.
1

Open connector settings

Go to Settings → Connectors → Personal connectors and click New MCP server.
2

Enter the server details

  • Server name: Superlines
  • Server URL: https://mcpsse.superlines.io?token=YOUR_API_KEY
  • Authentication: Select No authentication (the API key is included in the URL)
3

Add the server

Click Add. The Superlines server now appears in your list of personal connectors.
4

Use in your project

In any Lovable project, the Superlines tools are now available to the AI agent. Try prompting: “Use Superlines to show my brand visibility”
You can also use Bearer token authentication. Set the Server URL to https://mcpsse.superlines.io and enter your API key (format: sl_live_...) as the bearer token.

ChatGPT

Method: MCP Connector via Settings. Requires a ChatGPT Plus or Pro subscription with Developer Mode enabled.
1

Enable Developer Mode

In ChatGPT, go to your profile → Settings → Apps & Connectors → Advanced settings (at the bottom of the page) and toggle on Developer Mode.
2

Create a connector

Go to Settings → Apps & Connectors and click Create.
3

Enter the server details

  • Name: Superlines
  • Description: AI Search Intelligence — mentions, share of voice, citations and competitors
  • MCP Server URL: https://mcpsse.superlines.io?token=YOUR_API_KEY
4

Confirm and create

Check the confirmation box and click Create. You should see the available Superlines tools listed.
5

Start using Superlines

Open a new ChatGPT conversation, click the + button near the message composer, select More, then choose the Superlines connector. Try: “List my Superlines brands”
ChatGPT connectors require a remote HTTPS endpoint. Local npx servers do not work with ChatGPT. MCP support in ChatGPT is currently in beta and may evolve — check OpenAI’s documentation for the latest setup steps.

n8n

Method: MCP Client node over SSE. Use this when a marketing or agency workflow should pull Superlines data on a schedule — for example a Monday digest per brand or market into Slack, Teams or Sheets.
1

Add an MCP Client node

In an n8n workflow, add an MCP Client node. If an AI Agent should call Superlines as a tool, use MCP Client Tool instead and connect it to the agent.
2

Set the server

  • Server Transport: SSE
  • Endpoint: https://mcpsse.superlines.io
  • Authentication: Bearer Auth, with your Superlines API key (sl_live_...) as the token
You can also put the key in the URL and set authentication to None:
3

Choose a tool and run it

n8n loads the Superlines tools from the server. Pick one — for example list brands or a metrics query — fill in the parameters, and execute the node.A typical agency or enterprise workflow is: schedule trigger → MCP Client (period comparison for each brand or market) → Slack, email or a spreadsheet.
Parameter names in n8n are Server Transport, Endpoint (shown as MCP Endpoint URL in current n8n docs) and Authentication. If SSE does not connect, try the HTTP transport against the same endpoint. API keys are available on Growth and Enterprise.

VS Code

Method: SSE or local npx. The config format depends on your MCP extension (e.g., GitHub Copilot, Continue, Cline).
1

Open your MCP configuration

Check your MCP extension’s documentation for the config file location. Common locations include .vscode/mcp.json in your project root or the extension’s global settings.
2

Add the Superlines server

3

Restart VS Code

Restart VS Code for the changes to take effect.

Other MCP clients

Any MCP-compatible client can connect to Superlines using the SSE endpoint:
Add this URL as an SSE transport server in your client’s MCP configuration. Consult your client’s documentation for the specific config format. For clients that support local process-based connections, use the npm package:
Set the SUPERLINES_API_KEY environment variable to your API key.

API key permissions

By default, API keys have read-only access — they can query analytics data but cannot modify your account. To use the Account Management tools (creating brands, adding prompts, etc.), you need to enable write permissions on your API key.

How to enable write permissions

1

Go to Organization Settings

Open Organization Settings → API Keys in the Superlines dashboard.
2

Edit your API key

Click on the API key you use for MCP and open its permissions settings.
3

Enable write permissions

Toggle on the permissions you need:
  • write:brands — allows creating new brands/domains
  • write:prompts — allows adding, pausing, unpausing prompts and managing labels
4

Save and reconnect

Save your changes. No client restart is needed — permissions take effect immediately.

Available permissions

Write operations are rate-limited and audit-logged for security. Brand creation is limited to 5 per hour, and prompt operations to 100 per hour per organization. All write actions are recorded in your organization’s audit log.
Deletion is intentionally not supported via MCP to prevent accidental data loss. Use pause_prompts to temporarily disable prompts instead.

Verify the connection

After setting up your client:
  1. Start a new conversation
  2. Ask: “List my Superlines brands”
  3. The AI should call the list_brands tool and show your brands
If it works, try:
  • “Show me my brand visibility for the last 30 days”
  • “Who are my top competitors?”
  • “Find content opportunities where I have low visibility”

Troubleshooting

Never share your API key publicly. If compromised, revoke it immediately in Organization Settings and generate a new one.

Resources