Skip to main content
Glama
Tatsuya50

Google News MCP Agent

by Tatsuya50
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

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

Using uv (Recommended)

  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.

ParametersJSON Schema
NameRequiredDescriptionDefault
topicYes
max_resultsNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A3.5/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must disclose behavior. It explains the three main steps (fetch, embed, store) but lacks detail on side effects (e.g., data persistence, network requirements) or potential issues (rate limits, error handling).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single succinct sentence covering the core functionality with no unnecessary words. Efficiently communicates the pipeline.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 2 parameters and an output schema, the description covers the overall workflow. It mentions local storage, which is important. Minor gaps remain (e.g., return value, but output schema exists).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description only implicitly explains 'topic' by mentioning 'given topic'. The 'max_results' parameter is not described at all, despite 0% schema coverage. The description adds minimal value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool fetches news articles, generates embeddings, and stores them in ChromaDB. It distinguishes from the sibling 'search_news' by implying a storage capability.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool vs. the alternative 'search_news'. The description does not mention prerequisites, limitations, or scenarios where one is preferred over the other.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_newsC

Searches the stored news articles using semantic search.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYes
n_resultsNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

C2.8/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It only mentions 'semantic search' but does not disclose behavioral traits such as read-only nature, authorization requirements, or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single efficient sentence with no redundancy, though it could benefit from slightly more structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of two parameters and a sibling tool, the description is too minimal; it does not explain return values or provide usage context, even though an output schema exists.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and the description adds no meaning for the parameters 'query' or 'n_results', failing to compensate for the lack of schema documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'searches', the resource 'stored news articles', and the method 'semantic search', which distinguishes it from the sibling tool 'ingest_news'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus the alternative 'ingest_news' or any context on appropriate usage scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

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

  1. 2 tool updatesv0.1.0
    • First observedingest_news
    • First observedsearch_news
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

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 issues

Resources

Related MCP Connectors

Related MCP Servers

  • google-news-trends-mcp

    jmanek
    A
    license
    B
    quality
    A
    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
    218 PyPI
    89
    MIT

  • Personal Semantic Search MCP

    Ethan2298
    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
    -