Siteline Documentation - AI Search Analytics

The Model Context Protocol (MCP) is a standard for connecting Large Language Models (LLMs) to platforms like Siteline. Once connected, your AI assistants can query Siteline Agent Analytics and AI Visibility data on your behalf.

MCP Setup

Choose your MCP client and add Siteline using the instructions below.

Claude
Claude Code
Codex
Cursor
JSON

In Claude or Claude Desktop, open Settings > Connectors, then add a custom connector:

Name: Siteline
URL: https://mcp.siteline.ai/mcp

After saving the connector, use Claude’s connector authentication flow to log in to Siteline and approve read-only analytics access for your team.

Add the MCP server with:

claude mcp add --transport http siteline https://mcp.siteline.ai/mcp

Then authenticate from Claude Code:

/mcp

Add the MCP server with:

codex mcp add siteline --url https://mcp.siteline.ai/mcp

In Cursor, add Siteline as a remote MCP server from Settings > Tools & Integrations > MCP, or add this project configuration to .cursor/mcp.json:

{
  "mcpServers": {
    "siteline": {
      "url": "https://mcp.siteline.ai/mcp"
    }
  }
}

Cursor will open the OAuth flow when it first connects or when you run a Siteline tool.

Alternatively, add this configuration to .mcp.json:

{
  "mcpServers": {
    "siteline": {
      "type": "http",
      "url": "https://mcp.siteline.ai/mcp"
    }
  }
}

After configuring the MCP server, authenticate using your MCP client’s authentication flow.

Authentication

Some MCP clients automatically prompt you to log in during setup, while others require manual authentication steps. Authentication opens a browser window where you log in to Siteline and grant read-only analytics access for the selected team.

Siteline MCP does not require you to generate or paste a public API key into the MCP client.

Next steps

After you log in, check that the MCP server is connected. Depending on the client, you may need to restart it to connect and detect all tools after authorization. To verify the client has access to the MCP server tools, ask it to query Siteline using natural language. For example: “Summarize prompt performance for my product using Siteline MCP.”

What you can ask

Once connected, ask your AI tool in plain language. It picks the right tools and handles the details. Try prompts like these:

Agent Analytics

How has OpenAI bot traffic to my site changed over the last 3 months?
Compare AI-referred human visits week over week.
Which pages do AI crawlers hit most often?

AI Visibility

Summarize my prompt performance on ChatGPT over the last 30 days.
Which tracked prompts am I ranking worst on, and which competitors are beating me?
Show how my Gemini visibility trended last month.

Citations

What are the top pages citing my product in the last 30 days?
Which source domains mention my competitors but not me?
List the products most often mentioned alongside mine.

Available tools

The server exposes seven read-only tools. Your AI tool selects these automatically, you don’t need to call them by name. Each maps directly to an endpoint in the Reporting API, where you can find exact parameters and response fields.

Tool	Use it to
`list_products`	List authorized primary products, product IDs, and domains for the MCP connection.
`list_product_websites`	List active website domains and website IDs for a product.
`list_product_tracked_prompts`	List tracked prompt rows with platform, domain, position, visibility, rank, run count, and labels.
`summarize_product_prompt_performance`	Summarize aggregate prompt visibility, position, rank, and competitor count.
`analyze_product_prompt_trends`	Analyze daily prompt visibility, position, and rank trends.
`list_product_citations`	List citation source pages, source domains, or mentioned products.
`analyze_product_analytics_timeseries`	Analyze AI crawler and referred human traffic timeseries.

Security risks

Connecting any data source to an LLM carries inherent risks. Siteline MCP is read-only, but AI tools can still retrieve and summarize analytics data that your team has access to.

Prompt injection can trick an AI assistant into treating untrusted content as instructions. Review MCP tool calls before allowing them, especially in clients that can run tools automatically.

Recommendations

Review tool calls before approving them
Connect only MCP clients you trust
Use a Siteline team with the minimum data access needed
Remove the MCP server from clients that no longer need access
Revoke or reconnect the MCP client if you suspect a client token was exposed

​MCP Setup

​Authentication

​Next steps

​What you can ask

​Available tools

​Security risks

​Recommendations

MCP Setup

Authentication

Next steps

What you can ask

Available tools

Security risks

Recommendations