Skip to main content
Glama
eluc1a

MCP News Server

by eluc1a

news-mcp MCP server

mcp news server

IMPORTANT

  • Do not begin coding unless the user asks you to. If the user is asking a question about the code, answer the question - do not write or modify code unless explicitly asked.

Related MCP server: Juhe News MCP Server

Components

Resources

The server exposes news articles stored in a database via a resource URI:

  • news://{category}/{limit}: Retrieves a list of the latest articles for a given category.

    • {category}: Filters articles by category (e.g., tech, data_science, news). See tool description for full list.

    • {limit} (optional, default 10): Specifies the maximum number of articles to return.

  • Each returned article includes title, link, published date, and source.

Prompts

The server currently does not expose any prompts. (The summarization logic exists internally but is not available via an MCP prompt).

Tools

The server implements one tool:

  • summarize_news: Retrieves raw news articles from the database, allowing the client (LLM) to summarize them.

    • Takes optional category (string) and limit (integer, default 20) arguments.

    • Returns a list of article dictionaries, each containing id, title, link, published, source, and content.

    • Available categories: tech, data_science, llm_tools, cybersecurity, linux, audio_dsp, startups, news, science, research, policy.

Configuration

The server relies on a PostgreSQL database configured via the DATABASE_URL environment variable (defaults to postgresql://localhost/mcp_news).

The news_gatherer.py script (intended to be run separately/scheduled) populates the database from various RSS feeds.

Summarization logic (internal, not exposed via MCP) uses the OpenAI API, configured via the OPENAI_API_KEY environment variable.

Other configurations (via environment variables or defaults):

  • LOOKBACK_HOURS: How far back news_gatherer.py looks for new articles (default: 6).

  • SUMMARY_WORD_TARGET: Target word count for internal summarization (default: 500).

  • MAX_ARTICLES_PER_SUMMARY: Maximum articles included in one summary batch (default: 25).

  • KEYWORD_FILTER: Keywords used by internal summarization logic.

Quickstart

Install

Claude Desktop

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

Development

Building and Publishing

To prepare the package for distribution:

  1. Sync dependencies and update lockfile:

uv sync
  1. Build package distributions:

uv build

This will create source and wheel distributions in the dist/ directory.

  1. Publish to PyPI:

uv publish

Note: You'll need to set PyPI credentials via environment variables or command flags:

  • Token: --token or UV_PUBLISH_TOKEN

  • Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

npx @modelcontextprotocol/inspector uv --directory ~/dev/news-mcp run news-mcp 

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

Available Tools

1 tool
add-noteC

Add a new note

ParametersJSON Schema
NameRequiredDescriptionDefault
nameYes
contentYes

TDQS

C2.4/5.0
Behavior2/5

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

No annotations are provided, so the description carries full burden for behavioral disclosure. 'Add a new note' implies a write/mutation operation, but it doesn't specify permissions needed, whether it's idempotent, error handling, or what happens on success (e.g., returns an ID). This leaves critical behavioral traits undocumented, making it inadequate for safe invocation.

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 very concise—'Add a new note' is a single, straightforward phrase with no wasted words. It's front-loaded and easy to parse. However, it's arguably too brief, bordering on under-specification, which slightly reduces its effectiveness despite the efficiency.

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 tool has 2 required parameters, 0% schema coverage, no annotations, and no output schema, the description is incomplete. It doesn't address parameter meanings, behavioral aspects, or return values, making it insufficient for an agent to understand how to use the tool effectively in context.

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?

Schema description coverage is 0%, so the schema provides no parameter details. The description adds no information about the parameters—it doesn't explain what 'name' and 'content' represent, their formats, or constraints. This fails to compensate for the lack of schema documentation, leaving parameters semantically unclear.

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

Purpose3/5

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

The description 'Add a new note' states the action (add) and resource (note), making the basic purpose clear. However, it's somewhat vague—it doesn't specify what kind of note (e.g., text note, annotation, comment) or in what context (e.g., to a document, user profile). With no sibling tools, differentiation isn't needed, but the purpose lacks specificity beyond the minimal verb+resource pairing.

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?

The description provides no guidance on when to use this tool—it doesn't mention prerequisites, alternatives, or context for usage. With no sibling tools, there's no need to distinguish from alternatives, but it fails to offer any usage context, such as what system or entity the note is added to, leaving the agent with no hints about appropriate scenarios.

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

TDQS

C2.7/5.0
Disambiguation5/5

With only one tool, there is no possibility of confusion or overlap between tools. The single tool 'add-note' has a clear and distinct purpose that cannot be mistaken for any other tool in the set.

Naming Consistency5/5

The single tool name 'add-note' follows a consistent verb-noun pattern, and with only one tool, there is no inconsistency to evaluate. The naming is straightforward and predictable.

Tool Count2/5

A single tool is too few for a server named 'MCP News Server', which implies a broader scope related to news. This minimal toolset suggests an incomplete or trivial implementation that does not adequately cover the expected domain.

Completeness1/5

The tool surface is severely incomplete for a news server. It only allows adding notes, with no tools for retrieving, updating, deleting, or searching news items, nor any functionality specific to news like fetching headlines or articles. This leaves significant gaps that will cause agent failures.

Maintenance

ActivitySlowing
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • F
    license
    B
    quality
    C
    maintenance
    A Model Context Protocol server that enables large language models to access the latest trending news headlines and detailed content across various categories including recommended, domestic, technology, and sports news.
    2
  • A
    license
    Not graded
    quality
    D
    maintenance
    MCP server that provides Korean and global AI/tech news via 6 tools (categories, search, trending, article reading, daily briefing) without requiring an API key.
    1
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/eluc1a/mcp-news'

If you have feedback or need assistance with the MCP directory API, please join our Discord server