Trendpulse

MCP Version Python Version License

A powerful, robust Model Context Protocol (MCP) server that connects AI models to Google News RSS feeds and Google Trends. Easily pull historical weekly interest curves, calculate keyword growth rates, fetch trending queries, and analyze/summarize related articles using LLMs and NLP.

Features

• Google News Integration: Trawl feeds for articles by keyword, location, or topic, and fetch top news stories.
• Advanced Trends Analysis: Pull 5 years of weekly interest history, calculate growth velocities over custom windows, and retrieve real-time trending keywords.
• NLP & LLM Summarization: Summarize article payloads and extract key concepts using client-side LLM sampling or local NLP.
• Windows-Safe & Robust: Fully handles local session state, rates limits, and includes a fallback mechanism for sites that are difficult to scrape.

Installation

Using uv/uvx (recommended)

When using uv no specific installation is needed. We will use uvx to directly run mcp-trendpulse.

Using PIP

pip install mcp-trendpulse

After installation, you can run it as a script using:

python -m mcp_trendpulse

Configuration

Configure for Claude.app

Add to your Claude settings:

{
  "mcpServers": {
    "mcp-trendpulse": {
      "command": "uvx",
      "args": ["mcp-trendpulse@latest"]
    }
  }
}

{
  "mcpServers": {
    "mcp-trendpulse": {
      "command": "python",
      "args": ["-m", "mcp_trendpulse"]
    }
  }
}

Configure for VS Code

{
  "mcp": {
    "servers": {
      "mcp-trendpulse": {
        "command": "uvx",
        "args": ["mcp-trendpulse@latest"]
      }
    }
  }
}

{
  "mcp": {
    "servers": {
      "mcp-trendpulse": {
        "command": "python",
        "args": ["-m", "mcp_trendpulse"]
      }
    }
  }
}

Configure for Cursor Editor

Cursor supports MCP configuration globally or per-project:

• Global Config: Edit %USERPROFILE%\.cursor\mcp.json (Windows) or ~/.cursor/mcp.json (macOS/Linux).
• Project Config: Create a .cursor/mcp.json file inside your project root.

Add the following to the mcpServers object:

{
  "mcpServers": {
    "mcp-trendpulse": {
      "command": "python",
      "args": ["-m", "mcp_trendpulse"]
    }
  }
}

(Alternatively, you can open Cursor Settings -> Features -> MCP, and click "Add New Global MCP Server" to set it up via the UI).

Configure for Gemini / Antigravity IDE

If you are pair programming with Gemini in Antigravity IDE, add the server to your settings file at %APPDATA%\.gemini\antigravity-ide\mcp_config.json:

{
  "mcpServers": {
    "mcp-trendpulse": {
      "command": "python",
      "args": ["-m", "mcp_trendpulse"]
    }
  }
}

Configure for ChatGPT (OpenAI)

Because ChatGPT resides in the cloud, it requires your local MCP server to be exposed via a secure HTTPS tunnel (e.g., using ngrok or similar):

1. Expose Server via Tunnel: Start your local MCP server using an HTTP/SSE bridge or expose its stdio endpoint using a secure tunnel tool.
2. Enable Developer Mode in ChatGPT: Open the ChatGPT desktop app, go to Settings → Apps & Connectors, and toggle on Developer Mode.
3. Register the Connector: Click + New Server (or "Create Connector") and paste the public HTTPS URL where your tunnel is hosted.

Environment Variables and Proxies

If you experience rate limits (429 Client Error) from Google Trends, or if your server is running in an environment without direct internet access, you can configure environment variables and proxies in one of two ways:

Option A: Using a .env file (Recommended)

You can create a .env file in the workspace directory (where the server is executed) and define the variables there. The server will automatically load them at startup:

HTTP_PROXY=http://your-proxy-address:port
HTTPS_PROXY=http://your-proxy-address:port
GOOGLE_TRENDS_DELAY=2.0

Option B: Injecting via the client configuration

You can add environment variables directly to the "env" object in your Claude Desktop or VS Code JSON configuration:

      "env": {
        "HTTP_PROXY": "http://your-proxy-address:port",
        "HTTPS_PROXY": "http://your-proxy-address:port",
        "GOOGLE_TRENDS_DELAY": "2.0"
      }

On Windows, it is also recommended to pass system environment variables like PATH, USERPROFILE, LOCALAPPDATA, and APPDATA under the "env" block to ensure that internal Chromium browsers (used by Playwright) resolve and execute correctly:

      "env": {
        "PATH": "C:\\Windows\\system32;C:\\Windows;C:\\Windows\\System32\\Wbem;C:\\Windows\\System32\\WindowsPowerShell\\v1.0\\;C:\\Users\\<Username>\\AppData\\Local\\Microsoft\\WindowsApps;C:\\Users\\<Username>\\AppData\\Local\\Programs\\uv",
        "USERPROFILE": "C:\\Users\\<Username>",
        "LOCALAPPDATA": "C:\\Users\\<Username>\\AppData\\Local",
        "APPDATA": "C:\\Users\\<Username>\\AppData\\Roaming"
      }

Tools

The following MCP tools are available:

All of the news related tools have an option to summarize the text of the article using LLM Sampling (if supported) or NLP

CLI

All tools can be accessed from the command line using uv

uv run mcp-trendpulse
Usage: mcp-trendpulse [OPTIONS] COMMAND [ARGS]...

  Find and download news articles using Google News.

Options:
  --help  Show this message and exit.

Commands:
  keyword   Find articles by keyword using Google News.
  location  Find articles by location using Google News.
  top       Get top news stories from Google News.
  topic     Find articles by topic using Google News.
  trending  Returns google trends for a specific geo location.

Debugging

npx @modelcontextprotocol/inspector uvx mcp-trendpulse

To run from within locally installed project:

cd path/to/mcp-trendpulse
npx @modelcontextprotocol/inspector uv run mcp-trendpulse

Testing

cd path/to/mcp-trendpulse
python -m pytest