
Clarity Data Export MCP Server
A Model Context Protocol server that lets you fetch Microsoft Clarity analytics data through Claude for Desktop or other MCP-compatible clients, with support for filtering by dimensions and retrieving various metrics.
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
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
token
as a parameter when calling theget-clarity-data
tool
- 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
推荐服务器

Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。