tech-collector-mcp Server

MCP server that aggregates tech articles from multiple sources, summarizes content, and syncs with Notion.

javascript

GitHub Stars

javascript

Language

2 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "ruumalilja-tech-collector-mcp": {
      "command": "node",
      "args": [
        "/absolute/path/to/tech-collector-mcp/src/index.js"
      ],
      "env": {
        "PAGE_LIMIT": "3",
        "NEWSAPI_KEY": "YOUR_NEWSAPI_KEY",
        "QIITA_TOKEN": "YOUR_QIITA_TOKEN",
        "GEMINI_API_KEY": "YOUR_GEMINI_API_KEY",
        "ITEMS_PER_PAGE": "10",
        "NOTION_API_KEY": "YOUR_NOTION_API_KEY",
        "NOTION_DATABASE_ID": "YOUR_DATABASE_ID"
      }
    }
  }
}

You can run the tech-collector MCP server to fetch tech articles from multiple sources, summarize them with Gemini, and automatically sync them to a Notion database. It operates in zero‑server mode (JSON‑RPC over STDIO) and supports multi‑source aggregation, URL/article summarization, and simple personalized recommendations. This makes it easy to build AI-powered article pipelines without managing a traditional web server.

How to use

You will run the MCP server locally and interact with it through an MCP client or integration that can call its tools. The server exposes functions to fetch articles from Qiita, Dev.to, NewsAPI, and Hacker News, summarize articles (including arbitrary URLs), synchronize content to Notion, and generate simple recommendations based on reading history, rating, and tags. To perform a typical workflow, start by starting the server, then use the available tools to fetch data, summarize items, store them in Notion, and optionally run a full aggregation to sync all sources.

How to install

# 1) Clone the project
$ git clone https://github.com/RuumaLilja/tech-collector-mcp.git
$ cd tech-collector-mcp

# 2) Install dependencies
$ npm install   # or yarn install

# 3) Setup environment
$ cp .env.example .env
# Edit .env and fill in your API keys and IDs

# 4) Run MCP server (STDIO mode)
$ node src/index.js

Additional sections

Configuration notes and environment variables that you will use based on the setup include the following. These values are used by the MCP server to access external services and control how many items are fetched per page and how results are stored.

Environment variables you’ll configure in .env (examples shown as placeholders):

# ==== API Keys & Tokens ====
GEMINI_API_KEY=your_gemini_api_key_here     # Google Generative AI
NEWSAPI_KEY=your_newsapi_api_key_here       # NewsAPI.org
QIITA_TOKEN=your_qiita_token_here           # Qiita (optional)

# ==== Pagination Settings ====
PAGE_LIMIT=3        # Default fetch count per service
ITEMS_PER_PAGE=10   # Pagination unit

# ==== Notion Integration ====
NOTION_API_KEY=your_notion_api_key_here     # Notion Integration Token
NOTION_DATABASE_ID=your_database_id_here    # Article storage DB ID


## Available tools

### getQiitaRanking

Fetch Qiita popularity rankings to surface trending articles.

### getDevtoArticles

Retrieve Dev.to articles by tag or query.

### getNewsApiArticles

Obtain technology news items from NewsAPI.org.

### getHackerNewsTopStories

Get top stories from Hacker News.

### fetchAllArticles

Fetch all sources and aggregate the latest articles.

### summarizeUrlArticle

Summarize any given URL article using Gemini.

### syncArticleToNotion

Store a single article into a Notion database.

### aggregateArticles

Fetch all sources and synchronize them to Notion in a batch.

### recommendArticles

Provide simple recommendations based on reading history, ratings, and tags.

Built by

VeilStrat

AI signals for GTM teams