NYTimes Article Search MCP Server
This is a TypeScript-based MCP server that allows searching for New York Times articles from the last 30 days based on a keyword. It demonstrates core MCP concepts by providing:
- Tools for searching articles
- Integration with the New York Times API

Features
Tools
search_articles- Search NYTimes articles from the last 30 days based on a keyword- Takes
keywordas a required parameter - Returns a list of articles with title, abstract, URL, published date, and author
- Takes
Development
Install dependencies:
npm install
Build the server:
npm run build
For development with auto-rebuild:
npm run watch
Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
npm run inspector
The Inspector will provide a URL to access debugging tools in your browser.
Installation
Installing via Smithery
To install NYTimes Article Search for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install nyt --client claude
Manual Installation
To use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"nyt": {
"command": "node",
"args": ["path/to/your/build/index.js"],
"env": {
"NYTIMES_API_KEY": "your_api_key_here"
}
}
}
}
Environment Variables
Create a .env file in the root of your project and add your New York Times API key:
NYTIMES_API_KEY=your_api_key_here
Running the Server
After building the project, you can run the server with:
node build/index.js
The server will start and listen for MCP requests over stdio.
License
This project is licensed under the MIT License.
Recommend MCP Servers 💡
vectorize-io/vectorize-mcp-server
A Model Context Protocol (MCP) server implementation that integrates with Vectorize for advanced Vector retrieval and text extraction.
puremd-mcp
A Model Context Protocol (MCP) server that integrates with pure.md to provide web unblocking, scraping, and searching capabilities for LLM clients, enabling them to reliably access web content in markdown format.
@r-huijts/opentk-mcp
A Model Context Protocol (MCP) server providing access to Dutch parliamentary data (Tweede Kamer) through OpenTK . This server enables AI assistants to search, retrieve, and analyze parliamentary documents, activities, and information as published by parliament.
microsoft.docs.mcp
The Microsoft Learn MCP Server is a cloud-hosted service that enables AI agents like GitHub Copilot to access trusted and up-to-date information directly from Microsoft's official documentation, offering high-quality content retrieval, semantic understanding, and real-time updates.
pinecone-assistant
An MCP server for Pinecone Assistant, enabling AI agents and applications to retrieve context snippets and integrate with Pinecone's vector database capabilities.
@andrea9293/mcp-documentation-server
A TypeScript-based MCP server that provides document management and semantic search capabilities