MCP Goodnews는 좋고 긍정적이며 희망적인 뉴스를 제공하는 서버를 갖춘 간단한 모델 컨텍스트 프로토콜(MCP) 애플리케이션입니다. 이 도구는 NewsAPI 에서 뉴스 기사를 가져와 Cohere LLM을 사용하여 긍정적인 감정을 기준으로 상위 뉴스 기사의 순위를 매겨 반환합니다.
부정적인 뉴스가 헤드라인을 장식하는 세상에서, Goodnews MCP는 더욱 긍정적이고 희망적인 뉴스 기사에 주목하고자 합니다. 이 프로젝트는 이메일 구독자에게 매일 긍정적인 뉴스를 전달했던 GoodnewsFirst라는 이전 프로젝트에서 영감을 받았습니다. 정말 멋진 프로젝트였습니다! GoodnewsFirst는 대규모 언어 모델(LLM)의 최근 획기적인 발전보다 앞서 기존의 감정 순위 매기기 방식에 의존했지만, Goodnews MCP는 최신 LLM을 활용하여 제로샷(zero-shot) 환경에서 감정 분석을 수행합니다.
Related MCP server: mcp-rss-aggregator
mcp-goodnews 복제지엑스피1
다음 단계에서는 복제된 저장소의 위치에 대한 절대 경로를 제공해야 합니다.
# Navigate to the configuration directory
cd ~/Library/Application\ Support/Claude/config
# Edit the claude_desktop_config.json file
nano claude_desktop_config.json# Navigate to the configuration directory
cd %APPDATA%\Claude\config
# Edit the claude_desktop_config.json file
notepad claude_desktop_config.json그리고 Goodnews 에 대한 mcpServers 아래에 항목을 추가하고 싶을 것입니다.
{
"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>"
}
}
}
}Claude Desktop은 업데이트된 구성을 사용하여 mcp-goodnews 서버를 빌드하고 실행합니다. 성공하면 채팅 대화 창 오른쪽 하단에 망치 도구가 표시됩니다.
망치 도구 아이콘을 클릭하면 사용 가능한 MCP 도구를 나열하는 모달 창이 나타납니다. 거기에 fetch_list_of_goodnews 나열되어 있어야 합니다.
예시 프롬프트:
"오늘의 좋은 소식을 들려주세요."
"이번 주에 세상에서는 어떤 긍정적인 일이 일어났나요?"
"과학에 관한 희망찬 뉴스 기사를 들려주세요."
좋은 소식을 요청하면 애플리케이션은 NewsAPI에 최근 기사를 쿼리합니다.
Cohere LLM은 각 기사의 감정을 분석합니다.
기사는 긍정적인 감정 점수를 기준으로 순위가 매겨집니다.
클로드를 통해 가장 높은 순위의 좋은 소식을 여러분에게 전달해드립니다.
Goodnews MCP와 함께 긍정적인 마음을 유지하세요!
Fetch a list of headlines and return only top-ranked news based on positivity.
| Name | Required | Description | Default |
|---|---|---|---|
| category | No | all |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It mentions filtering by positivity but lacks details on permissions, rate limits, data freshness, or what 'top-ranked' entails (e.g., algorithm, recency). This leaves significant gaps for a tool that likely involves external data fetching.
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 a single, efficient sentence that gets straight to the point without unnecessary words. It's appropriately sized for a simple tool, though it could be slightly more informative without losing conciseness.
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 no annotations, no output schema, and low schema coverage, the description is incomplete. It doesn't explain return values, error handling, or behavioral traits like how 'positivity' is measured, making it inadequate for effective tool use.
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 description coverage is 0%, so the description must compensate. It doesn't mention the 'category' parameter at all, failing to add meaning beyond the schema. However, with only one parameter and an enum in the schema, the baseline is moderate, but the description offers no parameter context.
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 action ('fetch a list of headlines') and the resource ('top-ranked news based on positivity'), making the purpose understandable. However, it doesn't differentiate from siblings since there are none, and 'top-ranked' could be more specific about ranking criteria.
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?
No guidance is provided on when to use this tool versus alternatives, prerequisites, or contextual triggers. The description implies filtering by positivity but doesn't specify scenarios or limitations for usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0fetch_list_of_goodnewsScored across 1 tool
With only one tool, there is no possibility of confusion or overlap between tools. The tool has a clear, distinct purpose focused on fetching positive news headlines.
Since there is only one tool, naming consistency is inherently perfect. The tool name 'fetch_list_of_goodnews' follows a clear verb_noun pattern, making it predictable and readable.
A single tool is too few for a server named 'MCP Goodnews', which suggests a broader domain of positive news handling. This minimal set limits functionality and feels thin, lacking operations like filtering, searching, or managing news items.
The tool surface is severely incomplete for a news-related server. It only provides fetching of top-ranked positive news, with no ability to create, update, delete, or search news items, leaving significant gaps that could cause agent failures in broader workflows.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Dive into the latest and greatest from the tech world with our Hacker News MCP server.
Real-time Claude & Anthropic news from your own Claude — free, no API key.
A Model Context Protocol server for Wix AI tools
