What is Goodnews

MCP Goodnews is a Model Context Protocol (MCP) application designed to gather and share positive and uplifting news articles. It utilizes the NewsAPI to fetch news content and employs a Cohere LLM for sentiment analysis, ensuring that users receive the most positive articles available.

Use cases

This application is particularly useful for individuals seeking a break from negative news, offering them a way to stay informed about positive developments worldwide. Users can prompt the system with questions about uplifting stories or recent good news, making it an engaging tool for anyone interested in positive journalism.

How to use

To use MCP Goodnews, first clone the repository from GitHub. Next, set up your configuration in the Claude Desktop application by specifying the command to run the server and providing your NewsAPI and Cohere API keys. Finally, start Claude Desktop, and use the integrated tool to fetch good news by asking relevant questions.

Key features

Key features of MCP Goodnews include integration with NewsAPI for accessing current news articles, the application of a Cohere LLM for advanced sentiment analysis, and a user-friendly interface within Claude Desktop that allows easy access to the service through simple prompts for positive news.

Where to use

MCP Goodnews can be used on personal computers through the Claude Desktop application, making it accessible for anyone with the necessary API keys. It is designed for users who want to engage with positive news stories in a straightforward format, enhancing overall well-being.

MCP Goodnews

MCP Goodnews is a simple Model Context Protocol (MCP) application that features
a server for getting good, positive, and uplifting news. This tool fetches news
articles from the NewsAPI and uses a Cohere LLM to rank
and return the top news articles based on positive sentiment.

Read the blog post on Medium!

Motivation

In a world where negative news often dominates headlines, Goodnews MCP aims to
shine a light on more positive and uplifting news stories. This project was
inspired by an earlier initiative called GoodnewsFirst, which delivered positive
news daily to email subscribers — it was a really awesome project! While GoodnewsFirst
predated recent breakthroughs in Large Language Models (LLMs) and relied on
traditional methods for sentiment ranking, Goodnews MCP leverages modern LLMs to
perform sentiment analysis in a zero-shot setting.

Example Usage: MCP Goodnews with Claude Desktop

Requirements

• Cohere API Key
• NewsAPI Key
• Claude Desktop Application
• uv Python Project and Package Manager

Clone mcp-goodnews

# Clone the repository
git clone https://github.com/VectorInstitute/mcp-goodnews.git

In the next step, we’ll need to provide the absolute path to the location of this
cloned repository.

Update Claude Desktop Config to find mcp-goodnews

For Mac/Linux

# Navigate to the configuration directory
cd ~/Library/Application\ Support/Claude/config

# Edit the claude_desktop_config.json file
nano claude_desktop_config.json

For Windows

# Navigate to the configuration directory
cd %APPDATA%\Claude\config

# Edit the claude_desktop_config.json file
notepad claude_desktop_config.json

And you’ll want to add an entry under mcpServers for Goodnews:

{
  "mcpServers": {
    "Goodnews": {
      "command": "<absolute-path-to-bin>/uv",
      "args": [
        "--directory",
        "<absolute-path-to-cloned-repo>/mcp-goodnews/src/mcp_goodnews",
        "run",
        "server.py"
      ],
      "env": {
        "NEWS_API_KEY": "<newsapi-api-key>",
        "COHERE_API_KEY": "<cohere-api-key>"
      }
    }
  }
}

Start or Restart Claude Desktop

Claude Desktop will use the updated config to build and run the mcp-goodnews server.
If successful, you will see the hammer tool in the bottom-right corner of the chat
dialogue window.

Clicking the hammer tool icon will bring up a modal that lists available MCP tools.
You should see fetch_list_of_goodnews listed there.

Ask Claude for Good News

Example prompts:

• “Show me some good news from today.”
• “What positive things happened in the world this week?”
• “Give me uplifting news stories about science.”

How It Works

1. When you request good news, the application queries the NewsAPI for recent articles
2. The Cohere LLM analyzes the sentiment of each article
3. Articles are ranked based on positive sentiment score
4. The top-ranking good news stories are returned to you through Claude

License

Apache 2.0

Stay positive with Goodnews MCP!