clarity-api¶
Microsoft Clarity API + MCP Server + A2A Agent for the agent-utilities ecosystem — a typed, action-routed connector for the Clarity Data Export API.
Official documentation
This site is the canonical reference for clarity-api, maintained alongside every
release.
Overview¶
clarity-api wraps the Microsoft Clarity Data Export API
with typed, deterministic MCP tools and an optional Pydantic-AI agent server. It provides:
Api— a Python client (clarity_api.api_client.Api) composed from per-domain mixins. It validates credentials againstGET /projectsand exposesget_data_exportfor live dashboard insights.- Action-routed MCP tool — the consolidated, togglable
clarity_insightstool (CONCEPT:CLA-001) that minimizes token overhead in LLM contexts. - An A2A agent server — a Pydantic-AI graph agent (console script
clarity-agent) that calls the MCP tool surface and exposes an AG-UI web interface.
The connector remains inactive when credentials are absent: configure CLARITY_URL
and CLARITY_TOKEN to connect it to your Clarity project.
Explore the documentation¶
- Installation — pip, source, extras, and the prebuilt Docker image.
- Deployment — run the MCP and agent servers, Docker Compose.
- Usage — the MCP tools, the
Apiclient, and the CLI. - Overview — the action-routed tool surface and architecture.
- Concepts — the
CONCEPT:CLA-*registry.
Quick start¶
Connect it to a Clarity project:
export CLARITY_URL=https://www.clarity.ms
export CLARITY_TOKEN=<your-clarity-token>
clarity-mcp --transport streamable-http --host 0.0.0.0 --port 8000
See Installation and Deployment for the full matrix (PyPI extras, Docker image, all transports, the agent server).