Clarity MCP Server
by
Fetch Microsoft Clarity analytics data via a Model Context Protocol server, supporting dimension filters, metric selection, and integration with Claude for Desktop or any MCP‑compatible client.
Clarity MCP Server Overview
What is Clarity MCP Server about?
Provides a simple interface to query Microsoft Clarity’s data export API, allowing MCP clients to retrieve filtered analytics such as scroll depth, engagement time, and traffic metrics.
How to use Clarity MCP Server?
- Install – run
npm install -g @microsoft/clarity-mcp-serveror usenpx @microsoft/clarity-mcp-server. - Run – start the server with the required token, e.g.,
npx @microsoft/clarity-mcp-server --clarity_api_token=YOUR_TOKEN. - Configure – add the server entry to your MCP client configuration (Claude for Desktop, VS Code extension, etc.).
- Invoke – use the
get-clarity-datatool from the client, supplyingnumOfDays, optionaldimensions,metrics, and thetokenif not passed on the command line.
Key Features of Clarity MCP Server
- Query Clarity data with up to three dimensions (Browser, Device, Country/Region, OS, …).
- Retrieve a variety of metrics: scroll depth, engagement time, traffic, etc.
- Supports command‑line token provision or tool‑parameter token.
- Works with Claude for Desktop, generic MCP clients, VS Code extension, and other plugins.
- Limits: 10 API calls per project per day, 1‑3 day window, max 1,000 rows per request.
Use Cases of Clarity MCP Server
- Product analytics: Pull recent user interaction data for dashboards or reports.
- AI‑assisted insights: Enable Claude or other LLM assistants to answer data‑driven questions.
- Rapid prototyping: Use the server locally to experiment with Clarity metrics without building custom API calls.
- Team collaboration: Share the server via VS Code extension so all developers can query the same analytics.
FAQ from the Clarity MCP Server
Q: Do I need a Microsoft account? A: Yes, you must have a Clarity project and generate an API token in the project’s Settings → Data Export.
Q: How far back can I retrieve data? A: Only the previous 1 to 3 days are available through the export API.
Q: What if I need more than 1,000 rows? A: The server does not support pagination; you must narrow dimensions or metrics to stay within the limit.
Q: Can I run the server without installing globally?
A: Absolutely – npx @microsoft/clarity-mcp-server runs it directly without a global install.
Q: How do I integrate with Claude for Desktop?
A: Add the server configuration to claude_desktop_config.json as shown in the README, then restart Claude.
Clarity MCP Server's README
Microsoft Clarity Data Export MCP Server
This is a Model Context Protocol (MCP) server for the Microsoft Clarity data export API. It allows you to fetch analytics data from Clarity using Claude for Desktop or other MCP-compatible clients.
Features
- Query Microsoft Clarity analytics data through a simple interface
- Filter by up to 3 dimensions (Browser, Device, Country/Region, OS, etc.)
- Retrieve various metrics (Scroll Depth, Engagement Time, Traffic, etc.)
- Seamlessly integrates with Claude for Desktop and other MCP clients
Setup and Installation
Prerequisites
- Node.js v16 or higher
- A Microsoft Clarity account and API token
- Any MCP-compatible client (Claude for Desktop, etc.)
Installation
Option 1: Install via npm (recommended)
You can install and run this package directly using npm:
# Install globally
npm install -g @microsoft/clarity-mcp-server
# Run the server
clarity-mcp-server
Option 2: Run with npx without installing
You can run the server directly using npx without installing:
npx @microsoft/clarity-mcp-server
With either option, you can provide your Clarity API token using the --clarity_api_token parameter:
npx @microsoft/clarity-mcp-server --clarity_api_token=your-token-here
Option 3: Manual Installation
- Clone or download this repository
- Install dependencies:
npm install - Build the TypeScript code:
npm run build - Run the server:
npm start
Extension/Plugin Installation
Visual Studio Code Extension
Click the button above to install the Microsoft Clarity MCP server directly in Visual Studio Code.
Claude Desktop Plugin
Install from Claude's extension gallery:
- Open Claude Desktop.
- Navigate to File → Settings → Extensions.
- Search for Microsoft Clarity MCP Server.
- Click Install to add the extension.
- Configure your API Token. Follow the instructions in the API Token section to retrieve and set it up correctly.
Configuration
You can provide the Clarity data export API token in two ways:
-
Command Line Arguments:
npx @microsoft/clarity-mcp-server --clarity_api_token=your-token -
Tool Parameters:
- Provide
tokenas a parameter when calling theget-clarity-datatool
- Provide
Configuring MCP Clients
Generic MCP Client Configuration
MCP clients typically require configuration to connect to the server. Here's a general example of how to configure an MCP client:
{
"mcpServers": {
"@microsoft/clarity-mcp-server": {
"command": "npx",
"args": [
"@microsoft/clarity-mcp-server",
"--clarity_api_token=your-api-token-here"
]
}
}
}
The specifics of where and how to add this configuration will depend on your specific MCP client.
Claude for Desktop Configuration
To configure Claude for Desktop to use this server:
-
Open your Claude for Desktop configuration file:
- Windows:
%AppData%\Claude\claude_desktop_config.json - macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
-
Add the configuration shown in the generic example above
-
Save the configuration file and restart Claude for Desktop
Using the Server
When using an MCP client with this server configured, you can ask it to fetch Clarity data. For example:
"Can you fetch my Clarity data for the last day, filtered by Browser and showing Traffic metrics?"
The MCP client will then prompt you to run the get-clarity-data tool, which requires:
numOfDays: Number of days to retrieve (1-3)dimensions: Array of dimensions to filter by (optional)metrics: Array of metrics to retrieve (optional)
If you haven't configured your credentials via command-line arguments, you'll also need to provide:
token: Your Clarity API token
API Token
Getting Your API Token
To generate an API token:
- Go to your Clarity project
- Select Settings → Data Export → Generate new API token
- Provide a descriptive name for the token
- Save the generated token securely
Limitations
- Maximum of 10 API requests are allowed per project per day
- Data retrieval is confined to the previous 1 to 3 days
- Maximum of three dimensions can be passed in a single request
- The response is limited to 1,000 rows and can't be paginated
License
MIT
Clarity MCP Server Reviews
Login Required
Please log in to share your review and rating for this MCP.
Actions
Clarity MCP Server's Information
- Author
- microsoft
- Category
- Data & Analytics
- Language
- TypeScript
- License
- MIT License
- Version
- v1.0.5
- Stars
- 39
- Updated
- about 1 month ago
Configuration
{
"mcpServers": {
"@microsoft/clarity-mcp-server": {
"command": "npx",
"args": [
"@microsoft/clarity-mcp-server"
],
"env": {
"CLARITY_API_TOKEN": "<YOUR_API_TOKEN>"
}
}
}
}Configure Clients
Related MCP Servers
Discover more MCP servers with similar functionality and use cases
Vizro
by mckinsey
Build high-quality data visualization apps quickly with low‑code configuration, leveraging Plotly, Dash, and Pydantic while allowing deep customisation through Python, JavaScript, HTML, and CSS.
AntV Chart
by antvis
mcp-server-chart is a Model Context Protocol (MCP) server developed by AntV that generates over 25 types of visual charts. It provides robust chart generation and data analysis capabilities, integrating with various AI clients and platforms.
Data Exploration
by reading-plus-ai
mcp-server-data-exploration is an MCP server designed for autonomous data exploration on CSV-based datasets. It acts as a personal Data Scientist assistant, providing intelligent insights with minimal effort.
Wren Engine
by Canner
Wren Engine is a semantic engine designed for Model Context Protocol (MCP) clients and AI agents, enabling accurate and context-aware access to enterprise data.
QuickChart
by GongRzhe
A Model Context Protocol (MCP) server for generating various types of charts using QuickChart.io, enabling chart creation through MCP tools.
BigQuery
by ergut
mcp-bigquery-server is a Model Context Protocol (MCP) server that enables Large Language Models (LLMs) to securely and efficiently interact with Google BigQuery datasets. It acts as a translator, allowing LLMs to query and analyze data in BigQuery using natural language instead of SQL.
Mcp Vegalite Server
by isaacwasserman
Provides tools for saving data tables and generating Vega‑Lite visualizations via an MCP interface, supporting both textual specifications and PNG image output.
Google Analytics
by surendranb
Google Analytics MCP Server is a Python-based tool that enables Large Language Models (LLMs) to access and analyze Google Analytics 4 (GA4) data using natural language, providing conversational querying of over 200 GA4 dimensions and metrics.
Mcp Tinybird
by tinybirdco
Provides a Model Context Protocol server implementation for Tinybird, allowing analytics agents to forward data to Tinybird's platform.