parsely-mcp
MCP server that enables AI assistants to query Parse.ly analytics for top posts, authors, tags, referrers, content search, and social shares.
README
Parse.ly MCP Server
A Model Context Protocol (MCP) server that provides access to Parse.ly analytics API. This server enables AI assistants like Claude to query Parse.ly data for content analytics, referrers, search, and social shares.
Built with Claude Code - See CLAUDE.md for development guidance.
Features
- Dual Transport: Supports both stdio (for
npxusage) and Streamable HTTP transport - Analytics Tools: Get metrics for top posts, authors, and tags with date-based queries
- Referrer Data: Track traffic sources by type (social, search, other, internal)
- Content Search: Search through Parse.ly content
- Social Shares: View share counts across platforms
- Date Range Support: Query specific days or ranges for time-based comparisons
- Type-Safe: Built with TypeScript for reliability
- Well-Tested: Comprehensive unit tests with mocked API responses
- Docker Support: Easy containerized deployment with port exposure
Prerequisites
- Node.js >= 20.0.0
- Parse.ly API credentials (API key and secret)
- Get your credentials from https://dash.parse.ly/
Installation
Quick Start with npx
The easiest way to use this server is via npx. Add it to your MCP client configuration:
{
"mcpServers": {
"parsely": {
"command": "npx",
"args": ["parsely-mcp"],
"env": {
"PARSELY_API_KEY": "your_api_key_here",
"PARSELY_API_SECRET": "your_api_secret_here"
}
}
}
}
This uses stdio transport, which is the default and works with Claude Desktop, Claude Code, and other MCP clients.
Local Development
- Clone the repository:
git clone https://github.com/dailybeast/parsely-mcp.git
cd parsely-mcp
- Install dependencies:
npm install
- Create a
.envfile from the example:
cp .env.example .env
- Edit
.envand add your Parse.ly credentials:
PARSELY_API_KEY=your_api_key_here
PARSELY_API_SECRET=your_api_secret_here
PORT=8742
- Build the project:
npm run build
- Run the server:
# Stdio transport (default)
npm start
# HTTP transport
node dist/index.js --http
When using --http, the server starts on http://localhost:8742 with:
- MCP endpoint:
http://localhost:8742/mcp- Streamable HTTP transport (POST, GET, DELETE) - Health check:
http://localhost:8742/health- Server health status
Docker
- Build the Docker image:
docker build -t parsely-mcp .
- Run the container with environment variables:
docker run -e PARSELY_API_KEY=your_key -e PARSELY_API_SECRET=your_secret -p 8742:8742 parsely-mcp
Available Tools
The MCP server exposes the following tools:
get_analytics_posts
Get analytics data for top posts.
- Parameters:
days(number, default: 7),limit(number, default: 10),sort(string, optional)
get_analytics_authors
Get analytics data for top authors.
- Parameters:
days(number, default: 7),limit(number, default: 10)
get_analytics_tags
Get analytics data for top tags.
- Parameters:
days(number, default: 7),limit(number, default: 10)
get_referrers
Get referrer data showing traffic sources.
- Parameters:
days(number, default: 7),limit(number, default: 10),type(string, optional: "social", "search", etc.)
search_content
Search Parse.ly content.
- Parameters:
query(string, required),limit(number, default: 10)
get_shares
Get social share data for posts.
- Parameters:
days(number, default: 7),limit(number, default: 10)
Development
Available Scripts
npm run build # Compile TypeScript
npm run dev # Watch mode for development
npm run lint # Run ESLint
npm test # Run tests
npm run test:watch # Run tests in watch mode
npm run test:coverage # Generate coverage report
Running Tests
Tests use mocked Parse.ly API responses and don't require real credentials:
npm test
For tests that need environment variables:
PARSELY_API_KEY=test PARSELY_API_SECRET=test npm test
Configuration
All configuration is done via environment variables:
| Variable | Required | Default | Description |
|---|---|---|---|
PARSELY_API_KEY |
Yes | - | Your Parse.ly API key |
PARSELY_API_SECRET |
Yes | - | Your Parse.ly API secret |
PARSELY_API_BASE_URL |
No | https://api.parse.ly/v2 |
Parse.ly API base URL |
PORT |
No | 8742 |
Server port (HTTP mode only) |
API Documentation
For more information about the Parse.ly API:
Contributing
Contributions are welcome! Please ensure:
- All tests pass (
npm test) - Code is linted (
npm run lint) - TypeScript compiles without errors (
npm run build)
License
MIT License - see LICENSE for details
Support
For issues and questions:
- GitHub Issues: https://github.com/dailybeast/parsely-mcp/issues
- Parse.ly Documentation: https://docs.parse.ly/
Acknowledgments
- Built with Claude Code - AI-assisted development
- Model Context Protocol SDK - TypeScript SDK for MCP
- Parse.ly API - Content analytics platform
Development
This project uses CLAUDE.md for AI-assisted development guidance. The file contains:
- Architecture overview and code organization
- Common development commands
- Testing requirements and conventions
- Open-source best practices
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。