Allows Codeium's Windsurf IDE to query DataFast analytics through MCP tools.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@@datafast/mcp-server how many visitors did I get this month?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP (Model Context Protocol) server that exposes DataFast analytics as tools for AI assistants like Claude, Cursor, and others.
Ask your AI assistant questions like:
"How many visitors did I get this week?"
"What are my top referrers this month?"
"Show me revenue by country for Q4"
"Which pages have the highest conversion rate?"
"What's my real-time visitor count?"
Node.js 18.0.0 or later
A DataFast account with an API key
Related MCP server: Clamp Analytics MCP Server
Go to your DataFast dashboard → Settings → API Keys and create a new key.
npm install @datafast/mcp-serverAdd this to your .cursor/mcp.json:
{
"mcpServers": {
"datafast": {
"command": "npx",
"args": ["-y", "@datafast/mcp-server"],
"env": {
"DATAFAST_API_KEY": "df_your_api_key_here"
}
}
}
}Add this to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"datafast": {
"command": "npx",
"args": ["-y", "@datafast/mcp-server"],
"env": {
"DATAFAST_API_KEY": "df_your_api_key_here"
}
}
}
}Add this to your ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"datafast": {
"command": "npx",
"args": ["-y", "@datafast/mcp-server"],
"env": {
"DATAFAST_API_KEY": "df_your_api_key_here"
}
}
}
}Tool | Description |
| High-level metrics: visitors, sessions, bounce rate, revenue, conversion rate |
| Time series data (hourly/daily/weekly/monthly) for trend analysis |
| Top pages by visitor count with revenue attribution |
| Top traffic referrers with revenue attribution |
| Visitors and revenue by country |
| Visitors and revenue by city |
| Visitors and revenue by region/state |
| Visitors and revenue by browser |
| Visitors and revenue by device type |
| Visitors and revenue by OS |
| UTM campaign performance data |
| Goal completion data |
| Visitors and revenue by hostname |
| Current real-time visitor count |
| Real-time visitor locations with recent events |
| Website metadata (domain, timezone, currency) |
Tool | Description |
| Detailed visitor profile with identity, activity, and conversion predictions |
Tool | Description |
| Track a custom goal completion |
| Track a payment event for revenue attribution |
| Link a visitor to a user in your system |
Tool | Description |
| Delete goal events by date range, visitor, or goal name |
| Delete payment events by transaction ID, visitor, or date range |
All analytics tools support powerful filtering:
UTM parameters: utm_source, utm_medium, utm_campaign, utm_term, utm_content
Traffic sources: ref, source, via, referrer
Content: page, entry_page, hostname
Geography: country, region, city
Technology: browser, os, device
Date range: startAt, endAt (ISO 8601)
Pagination: limit, offset
Timezone: timezone (IANA format)
Variable | Required | Description |
| Yes | Your DataFast API key (starts with |
| No | API base URL (defaults to |
# Install dependencies
npm install
# Build
npm run build
# Type check
npm run typecheck
# Run locally
DATAFAST_API_KEY=df_your_key node dist/index.jsEnsure your AI client (Cursor, Claude Desktop, etc.) is configured to pass the DATAFAST_API_KEY in the env object. The key must start with df_.
DataFast API keys start with df_. Verify you copied the full key from the DataFast dashboard → Settings → API Keys.
Restart Cursor after adding the MCP config
Ensure the config file is at .cursor/mcp.json (or the path your Cursor version expects)
Check that npx can resolve @datafast/mcp-server (try running npx -y @datafast/mcp-server in a terminal with DATAFAST_API_KEY set)
If you see DataFast API error (401), your API key may be invalid or expired. Generate a new key from the dashboard. For DataFast API error (403), check that your API key has the required permissions.
MIT
Delete goal events. Filter by date range, visitor ID, or goal name. At least one filter must be provided.
Inputs: name, endAt, startAt, datafast_visitor_id.
Delete payment events. Filter by transaction ID, visitor ID, or date range. At least one filter must be provided.
Inputs: endAt, startAt, transaction_id, datafast_visitor_id.
Get visitor counts and revenue broken down by web browser (Chrome, Safari, Firefox, etc.).
Inputs: os, ref, via, city, +19 more.
Get visitor counts and revenue broken down by UTM campaign parameters (source, medium, campaign, term, content). Great for measuring marketing campaign performance.
Inputs: os, ref, via, city, +19 more.
Get visitor counts and revenue broken down by city.
Inputs: os, ref, via, city, +19 more.
Get visitor counts and revenue broken down by country. Returns country name, flag image URL, visitor count, and revenue.
Inputs: os, ref, via, city, +19 more.
Get visitor counts and revenue broken down by device type (desktop, mobile, tablet).
Inputs: os, ref, via, city, +19 more.
Get custom goal completion data including goal name, number of completions, and unique visitors who completed each goal.
Inputs: os, ref, via, city, +19 more.
Get visitor counts and revenue broken down by hostname (useful for multi-domain tracking).
Inputs: os, ref, via, city, +19 more.
Get metadata about the tracked website including domain, timezone, name, KPI settings, and currency configuration.
Inputs: no named parameters.
Get visitor counts and revenue broken down by operating system (Windows, macOS, iOS, Android, Linux, etc.).
Inputs: os, ref, via, city, +19 more.
Get high-level analytics metrics including visitors, sessions, bounce rate, average session duration, revenue, revenue per visitor, and conversion rate. Returns aggregate data for the specified time period.
Inputs: os, ref, via, city, +17 more.
Get the most visited pages on the website, ranked by visitor count. Includes hostname, path, visitor count, and revenue attribution per page.
Inputs: os, ref, via, city, +19 more.
Get the number of visitors currently active on the website in real time.
Inputs: no named parameters.
Get real-time visitor data with geographic coordinates for map visualization. Includes recent events, recent payments, and conversion predictions.
Inputs: no named parameters.
Get the top traffic referrers (sources linking to the website). Includes referrer URL, visitor count, and revenue attributed to each referrer.
Inputs: os, ref, via, city, +19 more.
Get visitor counts and revenue broken down by region/state.
Inputs: os, ref, via, city, +19 more.
Get time series analytics data with configurable intervals (hour, day, week, month). Returns visitors, sessions, revenue, and conversion rate over time. Great for trend analysis and charts.
Inputs: fields (required), interval (required), os, ref, +21 more.
Get detailed information about a specific visitor including their identity (country, browser, device), activity (visit count, page views, goals completed), and conversion predictions.
Inputs: visitorId (required).
Link a DataFast visitor to a user in your system. Associates the visitor ID with a user ID and optional metadata for enriched analytics.
Inputs: user_id (required), datafast_visitor_id (required).
Track a custom goal completion for a specific visitor. Goal names must be lowercase, alphanumeric with underscores/hyphens, max 64 characters.
Inputs: name (required), visitorId (required), metadata, description.
Track a payment event for revenue attribution. Links payments to visitors for conversion tracking.
Inputs: amount (required), currency (required), transaction_id (required), name, +7 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 22 tools
Most tools are clearly distinct, especially the get_* breakdowns which explicitly name their dimension (country, city, browser, etc.). Minor confusion could arise between get_realtime and get_realtime_map, but their outputs differ enough. The large family of similar analytics tools requires careful reading, but names and descriptions mitigate ambiguity.
All tool names follow a consistent lowercase_with_underscores pattern using verb_noun: get_* for retrievals, track_* for event creation, delete_* for deletions, and identify_visitor for association. This is highly predictable and consistent across the entire set.
At 22 tools, the server is on the heavier side but the count is justified by the wide range of analytics dimensions (countries, cities, browsers, devices, etc.) plus tracking and deletion operations. It exceeds the ideal 15-tool range but does not feel bloated for an analytics platform.
The analytics surface is broad, covering many breakdowns and real-time data. However, there are notable gaps: no get_payments to read payment events despite having delete_payments, and no list/search for visitors beyond fetching a single visitor by ID. These missing read operations create dead ends in the tracking lifecycle.
Query your Betterlytics web analytics from AI agents: traffic, funnels, journeys, errors, uptime.
AI access to Hitsteps analytics, live visitors, uptime, goals, alerts, and chats.
Marketing data and actions for AI agents: GA4, Search Console, ads, social, SEO and WordPress.
Ask your website analytics in plain language and set up funnels, features and dashboards.
