WhatsNew-MCPserver
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@WhatsNew-MCPservershow me AWS What's New for January 2026"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
WhatsNew-MCPserver
An MCP (Model Context Protocol) server that fetches AWS What's New announcements by month.
πΊπΈ English README | π°π· νκ΅μ΄ README
Overview
This server exposes a single MCP tool get_whats_new that queries the AWS What's New page via its internal JSON API and returns formatted results filtered by year/month.
Related MCP server: News Crawler MCP Server
Requirements
Python >= 3.10
Installation
git clone https://github.com/chhanz/WhatsNew-MCPserver.gitMCP Tool
get_whats_new
Parameter | Format | Example |
|
|
|
Returns a formatted list of AWS What's New entries for the specified month, including title, date, description, and link.
Usage
Kiro MCP Configuration
Add to your .kiro/settings/mcp.json:
{
"mcpServers": {
"whats-new-mcp": {
"command": "uvx",
"args": [
"--from", "/path/to/WhatsNew-MCPserver",
"whats-new-mcp"
],
"disabled": false,
"autoApprove": []
}
}
}Project Structure
WhatsNew-MCPserver/
βββ pyproject.toml
βββ README.md
βββ README-kr.md
βββ src/
βββ whats_new_mcp/
βββ __init__.py
βββ server.pyNotes
The API endpoint is an undocumented internal API used by the AWS website frontend. It may change without notice.
Monthly filtering is done client-side since the API only supports year-level tag filtering.
License
This project is licensed under CC BY-NC 4.0. Commercial use is not permitted.
Available Tools
1 toolget_whats_newA
Fetch news from AWS What's New API for a specific month.
Args: year_month: Year/month to query (format: YYYY/MM, e.g. 2026/01)
| Name | Required | Description | Default |
|---|---|---|---|
| year_month | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
| result | Yes |
TDQS
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. It only mentions fetching from AWS What's New API but does not disclose rate limits, authentication requirements, or error handling (e.g., invalid month format or no data). This leaves significant transparency gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise, with a clear one-line purpose followed by a parameter specification. Every sentence is necessary and the structure is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the presence of an output schema (evidenced by context signals), the description does not need to explain return values. However, it lacks mention of potential errors or limitations (e.g., what happens if the month has no news or the format is wrong), making it somewhat incomplete for a real-world usage scenario.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, meaning the schema only defines the parameter as a string without description. The description adds the required format (YYYY/MM) and an example, which provides meaningful guidance beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool fetches news from AWS What's New API for a specific month, using a specific verb and resource. With no sibling tools, differentiation is not required, and the description is unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indicates the tool is for fetching news for a specific month, but lacks guidance on when to use alternatives or when not to use it. Since there are no siblings, the need for exclusion is minimal, but still no explicit usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
Only one tool exists, so there is no risk of ambiguity.
With a single tool, naming consistency is trivially maintained.
A single tool feels too few for even a simple news service; users likely need additional operations like listing recent news or filtering by category.
The tool fetches news for a specific month, but lacks search, detailed item retrieval, or category filtering, which are notable gaps.
Maintenance
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
Hacker News MCP β search and retrieve stories from Hacker News
A paid remote MCP for AI SDK data query MCP, built to return verdicts, receipts, usage logs, and aud
Provide seamless access to Appfolio Property Manager Reporting API through a standardized MCP servβ¦
Fetch US Bureau of Labor Statistics data β CPI, unemployment, wages, JOLTS, and more via MCP.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceMCP server that fetches and filters AI-related news from 20+ RSS feeds with scheduled notifications and email digests.1
- FlicenseNot gradedqualityDmaintenanceEnables crawling news articles by category (politics, economy, society, etc.) and generates blog-ready markdown summaries. Provides MCP tools for listing categories, crawling news, getting article details, and saving to files.
- FlicenseNot gradedqualityCmaintenanceEnables global news retrieval across multiple countries and categories (world, country, technology, science) via RSS feeds, exposing reusable MCP tools for fetching and searching news articles with no API keys required.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/chhanz/WhatsNew-MCPserver'
If you have feedback or need assistance with the MCP directory API, please join our Discord server