MCP Server

Connect AI assistants to your MakinForU analytics data using the Model Context Protocol.

MakinForU exposes an MCP (Model Context Protocol) server that lets AI assistants — Claude, Cursor, Windsurf, and others — query your analytics data directly in conversation.

Endpoint

https://api.makinforu.com/mcp

Authentication

Pass the token as an Authorization header:

Authorization: Bearer YOUR_TOKEN

If your client can't set headers, pass it as a query parameter instead:

https://api.makinforu.com/mcp?token=YOUR_TOKEN

Both work. Prefer the header: query strings travel through browser history, shell history and proxy logs, so a token in the URL is easier to leak by accident.

Token format

The token is a base64-encoded string of your client ID and client secret joined by a colon:

base64(clientId:clientSecret)

From the dashboard

The easiest way to get your MCP token is directly from the dashboard — no terminal needed:

New client — after creating a client via Settings → API Clients, the success screen shows the MCP Token field ready to copy.
Onboarding — the connect step in the onboarding flow shows the MCP Token alongside your client ID and secret. Use the Save button to download all three values as credentials.txt.

From the terminal

echo -n "YOUR_CLIENT_ID:YOUR_CLIENT_SECRET" | base64

Then send it with every request:

Authorization: Bearer <base64-encoded-token>

Or, for clients that can't set headers, append it to the MCP URL:

https://api.makinforu.com/mcp?token=<base64-encoded-token>

Required client type

Only read and root clients can authenticate with MCP. Write-only clients are rejected.

Client type	Access
`read`	Scoped to a single project (the one the client belongs to)
`root`	Can query any project in your organization

Use a read client if you want to limit the AI assistant to one project. Use a root client if you need cross-project access or want to list all projects.

Go to Settings → API Clients in your dashboard to create a client. See the Authentication guide for more details.

Connecting to Claude Desktop

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "makinforu": {
      "type": "streamable-http",
      "url": "https://api.makinforu.com/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_TOKEN"
      }
    }
  }
}

If your client doesn't read headers, drop that block and put the token in the URL instead: "url": "https://api.makinforu.com/mcp?token=YOUR_TOKEN".

Connecting with Claude Code CLI

Use the --header flag to pass the token via Authorization: Bearer:

claude mcp add --transport http makinforu https://api.makinforu.com/mcp \
  --header "Authorization: Bearer YOUR_TOKEN"

Or with the token in the URL:

claude mcp add --transport http makinforu "https://api.makinforu.com/mcp?token=YOUR_TOKEN"

Available tools

Project access

Tool	Description
`list_projects`	List all projects accessible with your credentials. Root clients see all organization projects; read clients see only their own.
`get_dashboard_urls`	Get clickable dashboard links for the current project — overview, events, profiles, sessions, and deep-links to specific items.

Dashboards & reports

Tool	Description
`list_dashboards`	List all dashboards for a project.
`get_dashboard`	Get a dashboard with its complete report configurations and saved layouts.
`list_reports`	List all reports in a dashboard with their chart types and tracked events.
`get_report_data`	Execute a saved report and return its data (time-series, funnel, metric, etc.).

Dashboard management (root clients)

Tool	Description
`create_dashboard`	Create a dashboard in a project.
`update_dashboard`	Rename a dashboard.
`delete_dashboard`	Delete an empty dashboard, or delete it with its reports using `forceDelete`.
`create_report`	Add a saved chart to a dashboard.
`update_report`	Replace a saved chart's configuration.
`delete_report`	Delete a saved chart.
`duplicate_report`	Duplicate a saved chart in its dashboard.
`update_report_layout`	Set a saved chart's dashboard grid position and dimensions.
`reset_dashboard_layout`	Remove all saved chart layouts from a dashboard.

Discovery

Tool	Description
`list_event_names`	Get the top 50 most common event names in the project. Call this first if you don't know exact event names.
`list_event_properties`	List all property keys tracked for an event (or across all events).
`get_event_property_values`	Get all distinct values for a specific event property.

Events & sessions

Tool	Description
`query_events`	Query raw events with optional filters. Returns individual records with path, device, country, referrer, and custom properties.
`query_sessions`	Query sessions with optional filters. Each session includes duration, entry/exit pages, bounce status, and attribution data.

Profiles (users)

Tool	Description
`find_profiles`	Search and filter user profiles by name, email, location, inactivity, session count, or whether they performed a specific event.
`get_profile`	Get a specific user profile with their most recent events.
`get_profile_sessions`	Get all sessions for a user profile, ordered by most recent first.
`get_profile_metrics`	Get computed lifetime metrics for a user: sessions, pageviews, bounce rate, revenue, and more.

Groups (B2B)

Tool	Description
`list_group_types`	List all group types defined in the project (e.g. `company`, `team`). Call this first before querying groups.
`find_groups`	Search for groups by name, ID, or type.
`get_group`	Get a specific group with its properties and member profiles.

Aggregated metrics

Tool	Description
`get_analytics_overview`	Key metrics for a date range: visitors, pageviews, sessions, bounce rate, and avg session duration.
`get_rolling_active_users`	Time series of active users using a rolling window — DAU (1 day), WAU (7 days), or MAU (30 days).
`get_top_pages`	Most visited pages ranked by pageviews.
`get_page_performance`	Per-page bounce rate, avg session duration, sessions, and pageviews.
`get_page_conversions`	Pages ranked by how many visitors went on to convert after viewing them.
`get_entry_exit_pages`	Most common entry pages (session start) or exit pages (session end).
`get_top_referrers`	Top traffic sources broken down by referrer name and type.
`get_country_breakdown`	Visitor counts by country, region, or city.
`get_device_breakdown`	Visitor counts by device type, browser, or OS.

User behavior

Tool	Description
`get_funnel`	Analyze a conversion funnel between 2+ events — sign-up flows, checkout, onboarding.
`get_retention_cohort`	Weekly user retention cohort table showing long-term product stickiness.
`get_weekly_retention_series`	Week-over-week retention as a time series.
`get_user_last_seen_distribution`	Histogram of user recency — useful for churn analysis.
`get_user_flow`	Visualize user navigation flows as a Sankey diagram (before/after/between events).
`get_engagement_metrics`	Engagement metrics over time.

These tools require GSC to be connected for the project from the project's settings in the dashboard (the "Google Search" tab). On a self-hosted instance the integration must first be enabled by the operator.

Tool	Description
`gsc_get_overview`	GSC performance over time: clicks, impressions, CTR, and avg position.
`gsc_get_top_pages`	Top-performing pages from GSC ranked by clicks.
`gsc_get_page_details`	Detailed GSC performance for a specific page including all queries driving traffic to it.
`gsc_get_top_queries`	Top search queries ranked by clicks.
`gsc_get_query_opportunities`	Low-hanging-fruit SEO opportunities: queries ranking 4–20 with meaningful search volume.
`gsc_get_query_details`	Detailed GSC data for a specific search query with all pages that rank for it.
`gsc_get_cannibalization`	Queries where multiple pages on your site compete against each other in Google.

Rate limiting

60 requests per minute per client.