Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
MCP server for Bing Search API
This repo adds Bing search to MCP-compatible agents. It exposes web, news, and image search tools, plus rate limiting and error handling, so your assistant can look things up without leaving the chat.
Builders who want their agent to search Bing for web results, news, and images.
You can let your agent fetch current information and visual results without switching tools.
What it does
Web search tool
`bing_web_search` searches the web for general information, websites, and content.
News search tool
`bing_news_search` looks up recent articles and current events.
Image search tool
`bing_image_search` returns image search results for visual lookup.
Rate limiting
Limits request volume to reduce API abuse.
Error handling
Handles API and server errors with clearer failures for the client.
How to get it
- 1Install dependencies
uv venv source .venv/bin/activate # On Windows: .venv\Scripts\activate uv pip install -e .
- 2Run
uvx bing-search-mcp
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.

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
- Clone this repository
- 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"
}
}
}
}

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
- Visit Microsoft Azure Portal
- Create or sign in to your Azure account
- Create a new Bing Search resource
- Go to the resource and find your API key in the "Keys and Endpoint" section
License
Files in the repo
- assets
- mcp_server_bing
- .env.sample
- .gitignore
- .python-version
- .windsurfrules
- CLAUDE.md
- Dockerfile
- LICENSE
- pyproject.toml
- README.md
- smithery.yaml
- uv.lock
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More connectors
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
20 MB lightweight cross-platform database client for 90+ databases, including MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, and Dameng. Built-in AI, MCP Server, CLI, desktop and Docker. | 轻量级跨平台数据库管理工具,支持 MySQL、PostgreSQL、SQLite、Redis、MongoDB、达梦等 90+ 数据库,提供桌面端、Docker、CLI、内置 AI 助手和 MCP Server。