PlainSignal MCP Server

PlainSignal MCP Server

Provides tools for retrieving analytics reports and metrics from PlainSignal through the Model Context Protocol (MCP).

Category
访问服务器

README

PlainSignal MCP Server

This is a Model Context Protocol (MCP) server implementation for PlainSignal analytics data. It provides tools for retrieving analytics reports and metrics through the MCP protocol.

Setup

Installation

From npm (recommended)

# Install globally
npm install -g @plainsignal/plainsignal-mcp

# Or install locally in your project
npm install @plainsignal/plainsignal-mcp

From source

  1. Clone this repository
  2. Install dependencies:
npm install

This project uses ES modules instead of CommonJS. Make sure you're using a Node.js version that supports ES modules (Node.js 14+).

Usage

When installed from npm

# If installed globally
plainsignal-mcp --token <your_access_token>

# If installed locally
npx plainsignal-mcp --token <your_access_token>

# Or using an environment variable
export PLAINSIGNAL_TOKEN=<your_access_token>
plainsignal-mcp

When using from source

Run the server with your access token:

node src/index.js --token <your_access_token>

# Or using an environment variable
export PLAINSIGNAL_TOKEN=<your_access_token>
node src/index.js

You can also specify a custom API base URL:

node src/index.js --token <your_access_token> --api-base-url <api_base_url>

Or use the short format:

node src/index.js -t <your_access_token> -u <api_base_url>

Alternatively, set the access token and API base URL as environment variables and use the test script:

export PLAINSIGNAL_TOKEN=your_access_token
export API_BASE_URL=https://app.plainsignal.com/api/v1
./test.sh

By default, the server connects to https://app.plainsignal.com/api/v1.

MCP Server configs

Claude Desktop

Add this snippet to your claude_desktop_config.json:

{
  "mcpServers": {
    "plainsignal": {
      "command": "npx -y @plainsignal/plainsignal-mcp",
      "env": {
        "PLAINSIGNAL_TOKEN": "<YOUR_PLAINSIGNAL_TOKEN>"
      }
    }
  }
}

Available Tools

The server provides the following tools:

getReport

Retrieves an analytics report for a specified domain and time period.

Parameters:

  • organizationID: Organization ID
  • domainID: Domain ID
  • periodFrom: Report start datetime in RFC3339 format
  • periodTo: Report end datetime in RFC3339 format
  • periodSelection: Period type (m: month, y: year, d: day)
  • aggregationWindow: Data aggregation window (h: hour, d: day)
  • filters: (Optional) List of filters as key-value pairs

getSubReport

Retrieves detailed metrics for a specific aspect of analytics data.

Parameters:

  • organizationID: Organization ID
  • domainID: Domain ID
  • periodFrom: Report start datetime in RFC3339 format
  • periodTo: Report end datetime in RFC3339 format
  • periodSelection: Period type (m: month, y: year, d: day)
  • aggregationWindow: Data aggregation window (h: hour, d: day)
  • subReportType: Type of report (1: page, 2: entry page, etc.)
  • filters: (Optional) List of filters as key-values pairs
  • pagination: (Optional) Pagination controls with limit and offset

API Reference

This server communicates with the PlainSignal API. By default, it connects to https://app.plainsignal.com/api/v1, but you can configure the API endpoint in several ways:

  1. Use the --api-base-url command line option:

    node src/index.js --token <your_token> --api-base-url https://app.plainsignal.com/api/v1
    
  2. Set the API_BASE_URL environment variable:

    export API_BASE_URL=https://app.plainsignal.com/api/v1
    
  3. Pass a custom API base URL to the constructor when instantiating the server programmatically:

    const server = new PlainSignalStdioServer(token, 'https://app.plainsignal.com/api/v1');
    

For Developers

The server is implemented using the MCP SDK and communicates over STDIO.

Examples

An example client is provided to demonstrate how to use the MCP server:

# Set your access token
export PLAINSIGNAL_TOKEN=your_access_token

# Run the example client
npm run example

Or run the resources example client:

# Set your access token
export PLAINSIGNAL_TOKEN=your_access_token

# Run the resources example client
npm run resources-example

The example client demonstrates:

  1. Connecting to the MCP server
  2. Listing available tools
  3. Calling the getReport tool with sample parameters
  4. Processing and displaying the results

The resources example client demonstrates:

  1. Connecting to the MCP server
  2. Listing available resources
  3. Reading the listDomains resource
  4. Processing and displaying the results

License

This project is licensed under the MIT License - see the LICENSE file for details.

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
Kagi MCP Server

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。

官方
精选
Python
graphlit-mcp-server

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。

官方
精选
TypeScript
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选