Tariff News MCP Server
Description
# Tariff News MCP Server A specialized server for retrieving and analyzing tariff-related news using the Machine Conversation Protocol (MCP). ## Overview The Tariff News MCP Server provides a robust interface for AI agents to access up-to-date tariff news and reactions. It…
About
# Tariff News MCP Server A specialized server for retrieving and analyzing tariff-related news using the Machine Conversation Protocol (MCP). ## Overview The Tariff News MCP Server provides a robust interface for AI agents to access up-to-date tariff news and reactions. It supports both stdio and Server-Sent Events…
Details
- Author
- shanscar
- Downloads
- 146
- Categories
- Other
Jump to
- Dual transport support (stdio and SSE)
- Specialized get_tariff_reaction_news tool for tariff news
- Integration with DuckDuckGo search for current news
- Configurable time limits for news searches
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Tariff News MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Clone the repository, install dependencies with pip install -r requirements.txt and pip install -e ., then run the server with python -m tariff_news_server.server (stdio) or python -m tariff_news_server.server --transport sse (SSE). Configure it in your mcp_settings.json file under mcpServers.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"tariff news mcp server": {
"Tariff-News-MCP-Server": {
"command": "python",
"args": [
"-m",
"tariff_news_server.server"
]
}
}
}
}McpServers
{
"Tariff-News-MCP-Server": {
"command": "python",
"args": [
"-m",
"tariff_news_server.server"
]
}
}Tariff News MCP Server
A specialized server for retrieving and analyzing tariff-related news using the Machine Conversation Protocol (MCP).
Overview
The Tariff News MCP Server provides a robust interface for AI agents to access up-to-date tariff news and reactions. It supports both stdio and Server-Sent Events (SSE) transport methods, making it versatile for different integration scenarios.
Features
- Dual transport support (stdio and SSE)
- Specialized get_tariff_reaction_news tool for retrieving tariff-related news
- Integration with DuckDuckGo search for current news retrieval
- Configurable time limits for news searches
Installation
Clone the repository and install dependencies:
git clone https://github.com/shanscar/Tariff-News-MCP-Server.git
cd Tariff-News-MCP-Server
pip install -r requirements.txt
pip install -e .
Usage
Running with stdio transport (default)
python -m tariff_news_server.server
Running with SSE transport
python -m tariff_news_server.server --transport sse
Configuration
Add the following to your mcp_settings.json file:
"mcpServers": {
"tariff-news-server": {
"command": "python",
"args": [
"-m",
"tariff_news_server.server"
],
"env": {},
"disabled": false,
"alwaysAllow": []
}
}
Architecture
The server follows a structured workflow:
1. Receives tool requests from MCP clients
2. Processes requests through the appropriate transport layer
3. Executes the requested tool function (e.g., get_tariff_reaction_news)
4. Queries DuckDuckGo for relevant news articles
5. Processes and formats the results
6. Returns structured data to the client
Solution Diagram
Development Stack
- Language: Python
- IDE: VS Code with Roo Code
- Framework: MCP Python SDK
- AI Integration: Google Gemini 2.5 Pro
- Search Engine: DuckDuckGo News Service
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
