Microsoft Clarity for AI agents
Microsoft Clarity is a free analytics tool that captures heatmaps and session recordings to show how visitors use a website. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Microsoft Clarity.
Export behavior data for a period
Export heatmap and session metrics for a date range to analyze a page's performance, read-only.
Check engagement on a landing page
Pull engagement metrics for a specific page to see how visitors interact with it.
Summarize weekly traffic behavior
Export recent data to summarize how user behavior changed after a design update.
1 Microsoft Clarity actions, graded by risk.
Every Microsoft Clarity action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
0Look things up. Allowed by default.
- No read actions.
write
1Create and change things. Allow, or ask the user first.
- microsoft_clarity.data_exportData Export
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Microsoft Clarity in three steps.
- 01Your users connect Microsoft ClarityThey add their Microsoft Clarity api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “data Export” can wait for the user to approve.
- 03Any agent can actYour agent calls Microsoft Clarity through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('microsoft_clarity', { read: 'allow', write: 'ask', // data_export destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Microsoft Clarity connects.
Users add their Microsoft Clarity api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Microsoft Clarity connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Microsoft Clarity from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Microsoft Clarity and Arc0, answered.
Can I use Microsoft Clarity with Claude, ChatGPT or Cursor?
Yes. Connect Microsoft Clarity to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Microsoft Clarity actions you allow.
How do users connect Microsoft Clarity?
Users add their Microsoft Clarity api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Microsoft Clarity actions can my agent take?
1 in total: 0 read, 1 write and 0 destructive, such as “data Export”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Microsoft Clarity?
Yes. Allow read actions and deny writes in the Microsoft Clarity policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Microsoft Clarity too?
Yes. The same Microsoft Clarity connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Microsoft Clarity into your agent.
Your users connect Microsoft Clarity once, under your brand. Your agent gets 1 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan