Eesee Metrics
API

MCP Integration

Connect your Eesee Metrics analytics data to Claude, Cursor, and other AI tools

The Eesee Metrics MCP server lets you query your analytics data directly from AI tools that support the Model Context Protocol. Ask questions like "what were my top pages last week?" or "are there any active anomaly alerts?" without leaving your editor or chat.

Requirements

  • Plan: Pro or Scale
  • MCP token: generated from your dashboard (Settings → API Keys)

Generating an MCP token

  1. Go to Settings → API Keys in your dashboard
  2. Click Create API Key
  3. Select MCP as the token type
  4. Choose the site you want to connect
  5. Copy the token — you won't be able to see it again

Each MCP token is scoped to a single site.

Connection

Endpoint: https://app.eeseemetrics.com/api/mcp Transport: Streamable HTTP (MCP spec 2024-11-05) Authentication: Authorization: Bearer YOUR_MCP_TOKEN

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "eesee-metrics": {
      "type": "http",
      "url": "https://app.eeseemetrics.com/api/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_MCP_TOKEN"
      }
    }
  }
}

On macOS the config file is at ~/Library/Application Support/Claude/claude_desktop_config.json. On Windows it's at %APPDATA%\Claude\claude_desktop_config.json.

Cursor

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

{
  "mcpServers": {
    "eesee-metrics": {
      "url": "https://app.eeseemetrics.com/api/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_MCP_TOKEN"
      }
    }
  }
}

Claude Code (CLI)

claude mcp add eesee-metrics \
  --transport http \
  --url https://app.eeseemetrics.com/api/mcp \
  --header "Authorization: Bearer YOUR_MCP_TOKEN"

Other MCP clients

Use the streamable HTTP transport with:

  • URL: https://app.eeseemetrics.com/api/mcp
  • Header: Authorization: Bearer YOUR_MCP_TOKEN

Rate limits

PlanRequests per minute
Pro60
Scale200

Available tools

Pro + Scale

ToolDescription
get_overviewSessions, pageviews, unique visitors, bounce rate, avg session duration
get_top_pagesTop pages by session count (up to 50)
get_top_referrersTop referring domains
get_top_countriesTraffic breakdown by country
get_top_devicesDevice type breakdown (desktop / mobile / tablet)
get_goalsGoal conversion counts and rates
get_campaignsCampaign performance metrics (UTM)
get_performanceCore Web Vitals — LCP, CLS, INP at p50/p75 with ratings
get_active_alertsAll unresolved anomaly alerts
get_latest_reportLatest AI report (weekly, monthly, quarterly, or yearly)

Scale only

ToolDescription
get_retentionCohort retention data
get_funnelsFunnel conversion rates
get_errorsJavaScript error log
get_sessionsRecent user sessions with entry page, country, device, duration
get_compare_periodsSide-by-side metric comparison between two time periods
get_all_reportsList of all available AI reports
get_gsc_dataGoogle Search Console data (requires GSC integration)

Tool parameters

Most tools accept optional start_date and end_date parameters in YYYY-MM-DD format. When omitted, tools default to the last 7 days.

get_overview(start_date: "2025-03-01", end_date: "2025-03-28")
get_top_pages(limit: 20, start_date: "2025-03-01")
get_latest_report(cadence: "monthly")
get_sessions(limit: 10)

Example usage

Once connected, you can ask your AI assistant things like:

  • "What are my top 10 pages this month?"
  • "Are there any active anomaly alerts on my site?"
  • "Compare this week's sessions to last week's"
  • "What's my bounce rate trend and are there any Core Web Vitals issues?"
  • "Give me the latest weekly report summary"
  • "Which countries are driving the most traffic?"

The AI tool will call the appropriate MCP tools and synthesize the results into a plain-English response.

MCP Integration | Eesee Metrics