WebSearch MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@WebSearch MCP Serversearch for latest AI developments in healthcare"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
WebSearch MCP Server
A simple web search server that supports free search and converts URL content to Markdown. 中文
Features
Web Search: Perform web searches using different providers. Supported providers: Bing, Baidu, Google(with browser_use).
Markdown Conversion: Convert the content of a URL into Markdown format.
Wechat Official Account Articles: Search and retrive wechat official account articles content.
GitHub Search: Easily search for anything on GitHub — repositories, users, issues, and more.
Related MCP server: wechat-article-summarizer
Getting Started
Prerequisites
Python 3.12 or higher
uv for dependency management (or pip)
Installation
Clone the repository:
git clone https://github.com/Howe829/websearch-mcp-server.git cd websearch-mcp-serverInstall the dependencies using uv (Recomend):
uv venv && uv syncOr, if you prefer using pip:
pip install -r requirements.txt
Configuration
Create a
.envfile based on the.env.examplefile:cp .env.example .envModify the
.envfile with your desired settings:BING_SEARCH_BASE_URL="https://www.bing.com" LANGUAGE="en" CC="us" IMPERSONATE="edge" HOST=127.0.0.1 PORT=8002 SERVER_MODE=streamable-http
Usage
Run the server using uv:
uv run python server.pyOr run the server using python:
source .venv/bin/activate
python server.pyContribution
Contributions are welcome!
This project uses pytest for unit tests
uv pip install pytest
uv pip install pytest-asyncio
uv run pytestAnd use the ruff for code sytle formatting
uv pip install ruff
ruff format .use mcp inpector to debug this server
uv run fastmcp dev server.pyThis server cannot be deployed
Maintenance
Related MCP Connectors
Web search, URL content extraction to Markdown, site mapping, and recursive web crawler.
Jina AI Reader/Search MCP — turn any URL into clean LLM-ready markdown, plus web search.
Turn any URL into clean Markdown and structured data. Scrape, crawl, search and extract.
Read any web page as clean Markdown for AI agents: fetch, search, metadata, links. SSRF-safe.
Related MCP Servers
- AlicenseAqualityAmaintenanceThis server enables LLMs to retrieve and process content from web pages, converting HTML to markdown for easier consumption.1103,531 PyPI90,399MIT
- AlicenseNot gradedqualityDmaintenanceMCP server that enables AI agents to fetch and summarize WeChat public articles, supporting export to HTML, Markdown, Obsidian, Notion, and OneNote.5MIT
- AlicenseNot gradedqualityCmaintenanceAn MCP server that aggregates web search results from multiple engines and optionally renders pages to Markdown, providing a unified search interface.7 npm3ISC
- AlicenseAqualityBmaintenanceA production-ready MCP server for free web search, news search, and webpage content extraction using DuckDuckGo and Bing.410 npmMIT