MCP Goodnews

A simple MCP application that delivers curated positive and uplifting news stories.

python

46

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "vectorinstitute-mcp-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>"
      }
    }
  }
}

MCP Goodnews provides a dedicated MCP server that fetches positive news from NewsAPI and uses a Cohere language model to rank and return uplifting stories. It gives you a focused, sentiment-driven feed of good news via an MCP client integration.

How to use

You use the MCP Goodnews server through an MCP client. After you set up the server, a tool named fetch_list_of_goodnews becomes available in the client interface. You can ask the client to show you uplifting news by prompting for positive stories from today, this week, or about a specific topic like science.

How to install

Prerequisites you need to have before starting: Cohere API Key, NewsAPI Key, Claude Desktop Application, and uv Python project tooling.

Clone the MCP Goodnews repository to your local machine.

If you are using Claude Desktop, update its configuration to point to the MCP server you will run. Add an entry under mcpServers for Goodnews with the following values.

{
  "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>"
      }
    }
  }
}

Additional notes

How it works in practice: when you request good news, the server queries NewsAPI for recent articles, the Cohere LLM analyzes sentiment, articles are ranked by positive sentiment, and the top stories are returned to you through your MCP client. This provides a focused stream of uplifting content while keeping the process automated and scalable.

Available tools

fetch_list_of_goodnews

Tool exposed by the MCP client to retrieve the list of good news items available from the server