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., "@@lodd/mcp-server Show me the pages with the highest bounce rate"
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.
First-party web analytics for AI agents. You add a 2KB script, Lodd collects your site's traffic, and your agent queries your own data over MCP. It's the analytics platform, not a connector to one.
42 MCP tools covering traffic, events, funnels, conversions, sources, performance, and actor analytics. No dashboard. Your agent queries structured JSON directly.
npx -y @lodd/mcp-serverSet LODD_API_KEY in your environment. Get a key at lodd.dev.
Related MCP server: mcp-site-analyst
Add to your MCP config:
{
"mcpServers": {
"lodd": {
"command": "npx",
"args": ["-y", "@lodd/mcp-server"],
"env": {
"LODD_API_KEY": "your-api-key"
}
}
}
}Add https://api.lodd.dev/mcp as an MCP connector. OAuth handles auth automatically.
"How's traffic this week?"
"Show me the pages with the highest bounce rate"
"Build a funnel from homepage to signup to purchase"
"Which traffic sources drive the most conversions?"
"Something unusual is happening today. Investigate."
42 tools across analytics, breakdowns, events, conversions, actors, annotations, trackable links, and account management. Full reference at lodd.dev/docs.
Same data is also available via REST at api.lodd.dev/v1/. API docs at lodd.dev/api. OpenAPI spec at lodd.dev/openapi.yaml.
Free up to 2,500 events/month. EUR 9.99/month for 100K events. All tools included on both tiers.
Record a user-facing change that may affect analytics. Call after deploying changes to pages, flows, or tracking. Skip dependency updates, CI config, and refactors with no visible impact.
Inputs: site (required), content (required), timestamp.
Generate a new API key for the current user. Use this to create keys for managed agents, CI pipelines, or other tools that need access to your Lodd analytics. The key is shown only once — save it immediately.
Inputs: name.
Register a new website for analytics tracking. Returns the site ID, tracking secret, and the script tag to embed.
Inputs: name (required), domain (required).
Create a trackable link for campaign attribution. Append ?ld= to your destination URL when sharing — clicks are attributed to the source in analytics.
Inputs: site (required), source_type (required), destination_url (required), label.
Exclude an IP address from analytics tracking for a site. Prevents the user's own visits from appearing in the data. In Claude Code, detect the IP with curl -s api.ipify.org first. In conversation agents, ask the user to check their IP at api.ipify.org and paste it. Must be done per site.
Inputs: site (required), ip_address.
List distinct actors (opaque hashed identifiers) with their event counts, first/last seen, and total revenue. Actors are customer-hashed — Lodd never sees the original identifier. Only includes events where an actor was set.
Inputs: site (required), limit, period.
Get the event timeline for a specific actor hash. Shows all events in chronological order with properties and revenue. The actor is an opaque identifier — Lodd does not know who it represents.
Inputs: site (required), actor (required), limit, period.
Get weekly cohort retention by actor hash. Groups actors by the week they first appeared, then shows how many returned in weeks 1-4. Actors are opaque hashes — no personal data is stored or exposed. Requires 2+ weeks of data for meaningful results.
Inputs: site (required), period.
Get aggregate analytics for a site (visitors, page views, bounce rate, etc.) with automatic comparison to the previous period. Returns average_duration in seconds. Optional filters segment the result by country, browser, os, device type, UTM source, or referrer.
Inputs: site (required), period, filter_os, filter_browser, +4 more.
Show bot and crawler traffic that's been filtered from analytics. Groups by user agent, showing sessions, page views, countries, and first/last seen. Useful for understanding what's crawling your site (AI crawlers, search engines, SEO tools).
Inputs: site (required), limit, period.
Group pages by URL pattern and get aggregate metrics per group. Useful for comparing how blog vs docs vs app pages perform. Patterns use SQL LIKE syntax where % matches anything.
Inputs: site (required), groups (required), period, filter_os, +5 more.
Find which pages lead to a specific conversion event. Shows pages viewed before the event in the same session, with conversion rate and average time to convert. Useful for identifying high-converting content.
Inputs: site (required), event_name (required), limit, period.
Get visitor geography breakdown by country. Call twice with different periods (e.g. '2026-04-01..2026-04-07' vs '2026-04-08..2026-04-14') to compare growth across countries. Optional filters segment by browser, os, device type, UTM source, or referrer.
Inputs: site (required), limit, period, filter_os, +4 more.
Given a URL, show where visitors go next or if they leave the site. Useful for understanding why people leave key pages like /pricing. The '(exited)' row means the session ended after viewing that page.
Inputs: site (required), from_url (required), limit, period, +6 more.
Get entry pages (where sessions start) and exit pages (where sessions end). Shows which pages attract new visits and where users leave. Useful for identifying effective landing pages and high-exit pages that may need improvement. Optional filters segment by country, browser, os, device type, UTM source, or referrer.
Inputs: site (required), limit, period, filter_os, +5 more.
Get a summary of all custom events tracked on a site, showing event names with their total count and unique sessions. Optionally segment by country, browser, os, device type, UTM source, or referrer (matched against the session's page views).
Inputs: site (required), period, filter_os, filter_browser, +4 more.
Get individual custom event records with their properties. Optionally filter by event name.
Inputs: site (required), limit, period, event_name.
Given a target event (like 'signup_complete'), find what actions typically precede it. Shows both pageviews and events before the target, ranked by frequency. step_position=1 is immediately before the target event.
Inputs: site (required), target_event (required), limit, period, +7 more.
Get event counts bucketed over time for a specific event. Useful for seeing how event frequency changes. Optional filters segment by country, browser, os, device type, UTM source, or referrer (matched against the session's page views).
Inputs: site (required), event_name (required), period, interval, +6 more.
Compute a conversion funnel across an ordered sequence of pageview URLs and custom events. Returns per-step session counts and conversion rate relative to step 0. Steps must all occur within the same session, in order. Optional filters constrain which sessions enter the funnel.
Inputs: site (required), steps (required), period, filter_os, +5 more.
Get click data for a specific trackable link, including referrers and countries. Returns up to 1000 most recent clicks.
Inputs: link (required), period.
Get pages ranked by traffic. Call twice with different periods to compare page performance over time. Optionally filter by URL path and/or segment by country, browser, os, device type, UTM source, or referrer. Returns page titles when available.
Inputs: site (required), limit, period, filter_os, +6 more.
Get page load time metrics (average, median, p95) grouped by page URL, device type, country, or browser. Only includes data from pages with load time measurements. Useful for identifying slow pages and correlating performance with engagement.
Inputs: site (required), limit, period, group_by.
Get the number of currently active visitors on a site (visitors with activity in the last 5 minutes)
Inputs: site (required).
Find the most common page sequences visitors follow. Returns paths like '/blog → /pricing → /signup' with session counts. Useful for understanding navigation patterns and identifying the most common journeys to conversion.
Inputs: site (required), limit, period, filter_os, +7 more.
Classify sessions into engagement buckets: bounced (1 page), browsed (2-3 pages), engaged (4+ pages or event fired), converted (conversion event fired). Optionally specify which event defines 'converted'.
Inputs: site (required), period, filter_os, filter_browser, +5 more.
Quick today vs yesterday comparison: visitors, top referrer, top country, and duration trends
Inputs: site (required).
Compare traffic sources by conversion rate for a specific event. Shows which referrers, UTM campaigns, and trackable links drive the most conversions, plus average time to convert per source.
Inputs: site (required), event_name (required), limit, period.
Get browser, operating system, and device type distribution in one call. Optional filters segment by country, browser, os, device type, UTM source, or referrer.
Inputs: site (required), limit, period, filter_os, +5 more.
Get visitor and page view counts bucketed over time (hourly or daily). Returns an array of {date_label, page_views, unique_visitors} objects. Optional filters segment by country, browser, os, device type, UTM source, or referrer.
Inputs: site (required), period, interval, filter_os, +5 more.
Get traffic sources: referrers, trackable links, and UTM campaigns combined. Shows where visitors are coming from. Call twice with different periods to compare source mix over time. Optional filters segment by country, browser, os, device type, UTM source, or referrer.
Inputs: site (required), limit, period, filter_os, +5 more.
Get current month's event usage and plan limits. Returns plan type, events used, monthly limit, and percentage.
Inputs: no named parameters.
List annotations (deploy notes, change records) for a site within a time period.
Inputs: site (required), period.
List all API keys for the current user. Shows key prefix, name, creation date, and last used date. Does not reveal full keys.
Inputs: no named parameters.
List all users who have access to a site, with their roles (owner or member).
Inputs: site (required).
List all websites you have access to with their domains and IDs
Inputs: no named parameters.
List all trackable links for a site with their click statistics
Inputs: site (required), status.
Remove a user's access to a site. Only the site owner can do this. Cannot remove the owner.
Inputs: site (required), email (required).
Permanently deactivate an API key. The key will immediately stop working. Use list_api_keys to find key IDs. Cannot be undone.
Inputs: key_id (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Scored across 40 tools
Most tools have distinct purposes, but some overlap exists among analytics retrieval tools like get_analytics, get_snapshot, get_timeseries, and get_realtime, which could cause misselection if descriptions aren't carefully read. Overall, the set is well-differentiated.
All tool names follow a consistent verb_noun pattern in snake_case (e.g., get_analytics, create_annotation, list_members, share_site). No mixing of conventions, making it predictable for an agent.
40 tools is on the higher side, but each addresses a specific analytics need (events, funnels, sessions, actors, etc.). While somewhat heavy, it remains justified for a comprehensive analytics platform.
Covers a wide range of analytics functionality including site management, detailed queries, events, funnels, actors, and API key management. Missing some CRUD operations (e.g., update/delete site, edit annotations) but core workflows are well-covered.
Clamp Analytics MCP server: traffic, revenue, funnels, cohorts, errors, and search, for AI agents.
Real-time web analytics for AI agents: query traffic, funnels, revenue, and manage your sites.
Analytics your AI agent can actually use. Track, experiment, and optimize via MCP.
Web analytics for AI agents: realtime visitors, revenue, funnels and AI-detected site issues
