Editorial profile
Microsoft's local server wraps the Clarity data export API, session-recording discovery, project analytics, and documentation search. It gives growth and UX teams a conversational route into behavior data without replacing the Clarity interface.
Where Microsoft Clarity MCP fits
The useful question is not whether this mcp server can be installed. It is whether its scope matches a named workflow, keeps the authoritative system clear, and gives a reviewer enough evidence to trust the result.
- UX-friction investigation
- Traffic and device analysis
- Finding relevant session recordings
Documented capabilities
These are the practical capabilities described by the current public source. Confirm the exact tool surface, account limits, and enabled permissions in the client you plan to use.
- Query project analytics and behavior metrics
- List session recordings with filters
- Search Clarity documentation
Setup outline
Treat setup as a small integration project. Use a dedicated test identity, begin with the narrowest access available, and record who owns upgrades and credential revocation.
- Generate a data export API token in the Clarity project
- Run @microsoft/clarity-mcp-server with npx or install its extension
- Add the server and token to the chosen MCP client
What to check before adoption
Product documentation normally shows the happy path. The items below are the constraints or open questions most likely to affect a business rollout.
- API tokens are sensitive and should not be committed in client configuration.
- Session data can contain sensitive user context; apply the organization's privacy rules.
Botfinder's take
Microsoft Clarity MCP has the advantage of first-party provenance: the publisher controls the underlying product and its integration surface. That reduces one layer of ambiguity, but it does not remove the need to test permissions, failure handling, output quality, and the complete data path.
Start with a read or draft workflow where a person can compare the result with the source system. Add mutation only after the team can explain approvals, duplicate protection, partial failures, and recovery without relying on the model to infer whether a write succeeded.