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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.