Microsoft Clarity MCP
Let your AI agent watch how real users actually behave.
Heatmaps, session recordings, rage clicks, dead clicks, excessive scrolling — Clarity captures what users do, our MCP turns it into agent-callable insights for Claude, Codex, and Manus.
What is the Microsoft Clarity MCP?
The Microsoft Clarity MCP exposes Clarity's Data Export API as agent-callable tools. Your AI agent can pull heatmap insights, session metrics, and behavior signals (rage clicks, dead clicks, quick backs, excessive scrolling) by URL, segment, device, country, and traffic source — then synthesize UX recommendations or flag regressions automatically.
Core Capabilities
Everything your AI agent can do once this MCP is connected
Heatmap Insights
Pull aggregated click, scroll, and area data for any URL with segmentation.
Session Metrics
Total sessions, average duration, pages per session, bounce — segmented every way.
Rage Clicks
Identify pages and elements where users repeatedly click in frustration.
Dead Clicks
Detect non-interactive elements users mistakenly try to click.
Quick Backs & Scroll Depth
Surface pages users immediately leave or where they don't scroll past the fold.
Smart Segmentation
Filter by device, country, OS, browser, traffic channel, custom tags, and date range.
Tools Exposed to Your Agent
These are the callable functions your AI agent gets access to via MCP
clarity_get_metrics(numOfDays, dimensions, filters)clarity_get_top_pages(numOfDays, filters, limit)clarity_get_dead_clicks(numOfDays, urlFilter)clarity_get_rage_clicks(numOfDays, urlFilter)clarity_get_quick_backs(numOfDays, urlFilter)clarity_get_excessive_scrolling(numOfDays, urlFilter)clarity_get_javascript_errors(numOfDays, urlFilter)clarity_get_session_metrics(numOfDays, segments)clarity_compare_segments(numOfDays, segmentA, segmentB)clarity_get_top_referrers(numOfDays)Real-World Use Cases
How teams use this MCP to automate work end-to-end
Feature release UX check
Claude pulls rage/dead clicks for new feature pages 24h after launch and flags anomalies.
Funnel friction diagnosis
Codex correlates checkout abandonment with rage-click hotspots, drafts a fix backlog.
Heatmap-driven redesign
Manus pulls heatmap data per page, identifies low-engagement zones, drafts redesign briefs.
JS error monitoring
Claude monitors Clarity's JS error feed and opens GitHub issues with affected URLs.
Landing page diagnosis
Pull behavior metrics for paid landings, identify pages with high rage clicks, pause those campaigns.
Weekly UX briefing
Auto-generated UX health report every Monday: top friction points, week-over-week deltas, recommendations.
Compatible AI Agents
This MCP works with every major MCP-compatible AI agent and IDE
Native MCP support in Claude Desktop and Claude API
Multi-agent orchestration with full MCP tool access
Use the MCP directly inside Claude Code's terminal agent
Connect via MCP-compatible bridges and OpenAI Agents SDK
Autonomous browsing & task agents via MCP integration
AI-first IDEs with built-in MCP support
How We Deploy It
From zero to a live, agent-callable MCP — typically in under a week
Clarity project audit
We verify your Clarity project, confirm tracking is healthy, and identify segments to expose.
API token generation
We help you generate a Clarity Data Export API token and configure secure storage.
MCP deployment
Hosted MCP with daily quota management (Clarity allows 10 API calls per project per day) and intelligent caching.
Agent integration
Wire into Claude, Codex, Manus, or Cursor. Validate end-to-end with sample queries.
UX prompt library
We deliver prompts tuned for UX work: friction analysis, heatmap interpretation, weekly UX reports.
Pricing & Packages
Transparent, one-time setup with optional ongoing support
Setup
- Clarity MCP install
- API token setup
- 1 agent integration
- Quota dashboard
- 30-day support
Pro
- Everything in Setup
- Multi-project support
- Custom segment tools
- UX prompt library
- Multi-agent integration
- 90-day support
Managed
- Hosted & monitored
- Daily quota optimization
- Quarterly tool updates
- Priority support
Secure by Design
Credentials stored in encrypted vaults, OAuth where supported, scoped read/write permissions, full audit logs, and self-hosted deployment options. Your data never leaves your environment unless you authorize it.
Frequently Asked Questions
Ready to plug Microsoft Clarity MCP into your AI stack?
We handle setup, authentication, hosting, and agent configuration. You get an MCP your team's AI can call from day one.