Skip to main content
Glama
Google News MCP Agent

Google News MCP Agent

by Tatsuya50

Google News MCP Agent

An MCP (Model Context Protocol) server that fetches news articles from Google News, vectorizes them locally using ChromaDB, and allows for semantic search. This tool enables AI agents (like Claude) to stay updated with specific topics and query stored knowledge effectively.

Features

  • Ingest News: Fetch headlines and summaries from Google News by topic.

  • Local Vector Store: Automatically embeds and stores articles in a local ChromaDB instance (persisted in chroma_db/).

  • Semantic Search: Search through the ingested news using natural language queries to find relevant information.

  • Privacy First: Runs entirely locally (excluding the initial news fetch). No API keys required for embeddings (uses sentence-transformers).

Related MCP server: Personal Semantic Search MCP

Prerequisites

  • Python 3.10 or higher

  • uv (recommended) or pip

Installation

  1. Clone the repository:

    git clone https://github.com/Tatsuya50/google-news-mcp.git
    cd google-news-mcp
  2. Install dependencies:

    uv sync

Using pip

  1. Clone the repository and navigate to the directory.

  2. Install the required packages:

    pip install -r requirements.txt

Configuration (Claude Desktop)

To use this with Claude Desktop, add the following configuration to your MCP config file (typically ~/AppData/Roaming/Claude/claude_desktop_config.json on Windows):

{
  "mcpServers": {
    "google-news": {
      "command": "uv",
      "args": [
        "--directory",
        "C:\\Users\\YOUR_USERNAME\\path\\to\\google-news-mcp",
        "run",
        "python",
        "mcp_server.py"
      ]
    }
  }
}

Note: Replace C:\\Users\\YOUR_USERNAME\\path\\to\\google-news-mcp with the actual absolute path to this repository.

Tools

ingest_news

Fetches and indexes news articles.

  • topic: The topic to search for (e.g., "Generative AI", "Stock Market").

  • max_results: (Optional) Number of articles to fetch (default: 5).

search_news

Searches the stored local database.

  • query: The question or topic to search for (e.g., "What are the latest AI trends?").

  • n_results: (Optional) Number of results to return (default: 3).

Development

Run the server locally for testing:

uv run python mcp_server.py

Inspect the database contents:

uv run python inspect_db.py

Available Tools

2 tools
ingest_newsA

Fetches news articles from Google News for a given topic, generates vector embeddings, and stores them in a local ChromaDB database.

Inputs: topic (required), max_results. Returns: result

search_newsC

Searches the stored news articles using semantic search.

Inputs: query (required), n_results. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: one fetches and stores news, the other searches stored articles. No overlap exists.

    Naming Consistency5/5

    Both tools follow the verb_noun pattern consistently: ingest_news and search_news.

    Tool Count4/5

    Two tools is minimal but appropriate for the narrow scope of fetching and searching news. It's slightly thin but not excessive.

    Completeness3/5

    The tools cover the basic workflow of ingesting and searching, but lack operations like deleting stored articles or listing topics, which are minor gaps.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      C
      maintenance
      Search and retrieve news articles and trending keywords from Google News and Google Trends. Summarize articles and extract keywords using optional NLP and LLM Sampling to get concise insights.
      5
      208 PyPI
      88
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables semantic search over local notes and documents using natural language queries. Supports multiple file types (Markdown, Python, HTML, JSON, CSV, text) with fast local embeddings and persistent ChromaDB vector storage.
      1
      -