mcpField
B
Bing Search MCP Server

Bing Search MCP Server

Local
github.com/leehanchungSearch81Updated 82w ago
Repository

About Bing Search MCP Server

Bing Search MCP Server is an MCP server for the Microsoft Bing Search API that lets AI assistants run web, news and image searches. It includes rate limiting and error handling and requires a Bing API key.

Key features

  1. 01Web search
  2. 02News search with freshness filter
  3. 03Image search
  4. 04Rate limiting
  5. 05Error handling

Use cases

  1. 01Letting an AI assistant look up general web information
  2. 02Checking recent news and current events
  3. 03Finding images through an AI assistant

MCP support

This project is an MCP server that exposes bing_web_search, bing_news_search and bing_image_search tools to MCP clients.

#mcp#claude#mcp-server

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "bing-search": {
      "command": "uvx",
      "args": [
        "bing-search-mcp"
      ],
      "env": {
        "BING_API_KEY": "<BING_API_KEY>"
      }
    }
  }
}
Run commanduvx bing-search-mcp
Environment variables to set
BING_API_KEYSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypibing-search-mcp

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Bing Search MCP Server

A Model Context Protocol (MCP) server for Microsoft Bing Search API integration, allowing AI assistants to perform web, news, and image searches.

smithery badge

Bing Search MCP Server

Features

  • Web search for general information
  • News search for recent events and timely information
  • Image search for visual content
  • Rate limiting to prevent API abuse
  • Comprehensive error handling

Requirements

  • Python 3.10 or higher
  • Microsoft Bing Search API key
  • MCP-compatible client (e.g., Claude Desktop, Cursor)

Installation

  1. Clone this repository
  2. Install dependencies: 
    uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate
uv pip install -e .

Configuration

Set the required environment variables:

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/

Usage

Running the server
uvx bing-search-mcp
Configuring with Claude for Desktop

Add the following to your Claude Desktop configuration file (~/Library/Application Support/Claude/claude_desktop_config.json on macOS or %APPDATA%\Claude\claude_desktop_config.json on Windows):

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

Claude Code Bing Search MCP

Available Tools

1. bing_web_search

General web search for information, websites, and content.

bing_web_search(query: str, count: int = 10, offset: int = 0, market: str = "en-US")
2. bing_news_search

Search for news articles and current events.

bing_news_search(query: str, count: int = 10, market: str = "en-US", freshness: str = "Day")
3. bing_image_search

Search for images.

bing_image_search(query: str, count: int = 10, market: str = "en-US")

Getting a Bing API Key

  1. Visit Microsoft Azure Portal
  2. Create or sign in to your Azure account
  3. Create a new Bing Search resource
  4. Go to the resource and find your API key in the "Keys and Endpoint" section

License

MIT License

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.