aibrief-mcp

aibrief-mcp

Read-only MCP server that serves curated daily Korean AI briefings (papers, releases, community, video, deepdive) via 7 tools, with no LLM calls per request.

Category
Visit Server

README

<img src="assets/icon.png" alt="aibrief-mcp" width="96" align="right" />

aibrief-mcp

매일 큐레이션된 한국어 AI 브리핑을 읽기 전용 MCP 툴로 노출하는 원격 서버. Cloudflare Workers(무상태 createMcpHandler)로 배포하고, Smithery에 URL 을 등록해 배포·발견한다.

상위 파이프라인 aibrief(수집→랭킹→요약, 비공개)가 만든 정본 JSON을 이 repo 의 data/(공개 아카이브)에 미러링하고, 서버는 그것을 런타임에 읽는다. 요약이 이미 계산돼 있어 요청당 LLM 호출·과금 0 — stateless·read-only.

툴 (7, 전부 read-only)

조회list_briefs · get_brief(date="latest") · get_section(date, section) · search_briefs(query, section?, tag?) 발견top_items(days=7, section?) · list_tags() · get_stats()

각 항목은 aibrief CuratedItem: title_ko·summary_ko·why_it_matters·tags·url·score.

구조

src/index.ts        # Cloudflare Worker — createMcpHandler, 7툴 (POST /mcp)
wrangler.jsonc      # Worker 설정 (compatibility_flags: nodejs_compat, var DATA_BASE_URL)
data/daily/*.json   # aibrief 정본 미러 (cron 이 매일 push)
data/index.json     # 일자 매니페스트                ← 생성물
data/search.json    # 평면 검색 인덱스               ← 생성물
data/stats.json     # 사전계산 집계(태그·섹션·기간)  ← 생성물 (list_tags·get_stats 용)
scripts/build_index.py  # data/daily → index/search/stats 재생성 (표준 라이브러리만)

데이터는 번들이 아니라 런타임에 raw 에서 fetch(base = DATA_BASE_URL) → cron 이 새 일자를 push 하면 재배포 없이 반영. 같은 URL 60초 캐시.

배포 (Cloudflare Workers)

Git 연결(권장, 로컬 CLI 불필요): Cloudflare 대시보드 → Workers → Import a repository → 이 repo 선택 → 빌드·배포. 이후 main 에 코드 push 시 자동 재배포. (데이터 push 는 [skip ci] 커밋이라 재배포 안 함.)

CLI:

npm install
npx wrangler deploy      # → https://aibrief-mcp.<subdomain>.workers.dev

배포되면 엔드포인트 https://.../mcpsmithery.ai/new(Publish → MCP) 의 MCP Server URL 에 등록 → Smithery 가 스캔해 툴 목록·Playground·호출 통계를 제공.

로컬 개발

npm install
npm run dev              # wrangler dev — 로컬 http://localhost:8787/mcp

인덱스 재생성 / 동기화

data/daily/ 가 바뀌면 python scripts/build_index.pyindex.json·search.json 재생성. aibriefdaily.yml 이 발행 직후 그날 JSON 을 이 repo 로 push + 인덱스 재생성한다(ADR-008).

공개 범위 (aibrief ADR-008)

공개되는 것은 ① 서빙 코드② 브리핑 콘텐츠(JSON) 뿐 — 수집 로직·랭킹·프롬프트·하네스는 aibrief(private)에 남는다.

License

MIT (서버 코드). 브리핑 콘텐츠는 3rd-party 소스의 요약을 포함한다.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured