Bing Search MCP Server

SearchPython

Enables AI assistants to perform web, news, and image searches using Microsoft Bing Search API

Available Tools

bing_web_search

Performs a general web search for information, websites, and content

querycountoffsetmarket

bing_news_search

Searches for news articles and current events

querycountmarketfreshness

bing_image_search

Searches for images

querycountmarket

The Bing Search MCP server provides AI assistants with the ability to search the web for information, news articles, and images using Microsoft's Bing Search API. This integration allows AI models to access up-to-date information from the internet, enhancing their ability to provide relevant and timely responses. With support for general web searches, news searches with freshness filtering, and image searches, this MCP server offers comprehensive search capabilities. The implementation includes rate limiting to prevent API abuse and robust error handling to ensure reliable operation.

Overview

The Bing Search MCP server integrates Microsoft's Bing Search API with AI assistants, allowing them to perform web searches, news searches, and image searches. This enables AI models to access current information from the internet, significantly enhancing their capabilities.

Prerequisites

Before installing the Bing Search MCP server, you'll need:

Python 3.10 or higher
A Microsoft Bing Search API key
An MCP-compatible client (such as Claude Desktop or Cursor)

Getting a Bing API Key

To use this MCP server, you'll need to obtain a Bing API key:

Visit the Microsoft Azure Portal
Create or sign in to your Azure account
Create a new Bing Search resource
Navigate to the resource and find your API key in the "Keys and Endpoint" section

Installation

Step 1: Clone the Repository

First, clone the repository to your local machine:

git clone https://github.com/leehanchung/bing-search-mcp.git
cd bing-search-mcp

Step 2: Set Up a Virtual Environment and Install Dependencies

The project uses uv for dependency management:

uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
uv pip install -e .

Step 3: Configure Environment Variables

Set the required environment variables:

For Linux/macOS:

export BING_API_KEY="your-bing-api-key"
export BING_API_URL="https://api.bing.microsoft.com/"  # Optional

For Windows:

set BING_API_KEY=your-bing-api-key
set BING_API_URL=https://api.bing.microsoft.com/

Running the Server

To start the MCP server:

uvx bing-search-mcp

Client Configuration

Claude Desktop

To configure Claude Desktop to use this MCP server, add the following to your Claude Desktop configuration file:

On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "bing-search": {
      "command": "uvx",
      "args": [
        "/path/to/your/bing-search-mcp"
      ],
      "env": {
        "BING_API_KEY": "your-bing-api-key"
      }
    }
  }
}

Replace /path/to/your/bing-search-mcp with the actual path to the repository on your system, and your-bing-api-key with your Bing API key.

Usage Tips

For general information, use the bing_web_search tool
For recent events and timely information, use the bing_news_search tool
For visual content, use the bing_image_search tool
The count parameter controls how many results are returned
The market parameter can be adjusted for region-specific results (default is "en-US")
For news searches, the freshness parameter can be set to "Day", "Week", or "Month" to control how recent the news articles should be