mcp-search-linkup
# 🌟 Linkup Python MCP Server
> ⚠️ **DEPRECATED**: This package is no longer maintained.
>
> Please use the TypeScript/Node.js version instead: **https://github.com/LinkupPlatform/linkup-mcp-server**
>
> The TypeScript version is actively maintained, has better performance, and supports all the latest features.
A Model Context Protocol (MCP) server that provides web search capabilities through Linkup's advanced search API. This server enables AI assistants and development tools to perform intelligent web searches with natural language queries.
<a href="https://glama.ai/mcp/servers/69qbbv8hl9"><img width="380" height="200" src="https://glama.ai/mcp/servers/69qbbv8hl9/badge" alt="mcp-search-linkup MCP server" /></a>
## ✨ Why Linkup?
- 🔍 **Advanced Web Search**: Leverage Linkup's AI-powered search engine for high-quality, relevant results
- 💬 **Natural Language Queries**: Ask questions in plain English or your preferred language - no need for keyword optimization
- 🚀 **Real-time Information**: Access up-to-date web content and current information
- 📚 **Comprehensive Results**: Get detailed search results with source citations
- 🔧 **Easy Integration**: Works with any MCP-compatible client
## 🚀 Installation
The Linkup MCP server can be used with any MCP-compatible client.
For an integration with Claude Desktop or with Cursor, please follow instruction [here](https://docs.linkup.so/pages/integrations/mcp/mcp).
For other MCP-compatible clients, use these connection details:
- **Command**: `python -m linkup_mcp_server`
- **Required Environment Variables**: `LINKUP_API_KEY`
Consult your MCP client's documentation for specific configuration instructions.
## 💬 Example Queries
The Linkup MCP server excels at answering complex questions and finding specific information:
- "What are the latest developments in quantum computing?"
- "How does the EU AI Act affect startups?"
- "Find recent research on sustainable aviation fuel"
- "What are the current best practices for MCP server development?"
## 🤝 Contributing
Pull requests are welcome! Feel free to open an issue first to discuss what you’d like to see improved.
## 📚 Resources
- [Linkup Documentation](https://docs.linkup.so)
- [MCP Protocol Specification](https://modelcontextprotocol.io)
- [Linkup API Reference](https://docs.linkup.so/api-reference)
## 📣 Community & Support
* Email: [support@linkup.so](mailto:support@linkup.so)
* Discord: [Join our community](https://discord.com/invite/9q9mCYJa86)
* X / Twitter: [@Linkup_platform](https://x.com/Linkup_platform)
## 📄 License
This project is licensed under the MIT License - Innovate freely! 🚀
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The tool 'search-web' has a clear, distinct purpose focused on web searching.
Since there is only one tool, naming consistency is inherently perfect. The tool name 'search-web' follows a clear verb-noun pattern and is straightforward.
A single tool is too few for most server purposes, as it severely limits functionality and scope. This feels thin and incomplete for a search-oriented server, lacking operations like filtering, advanced queries, or result management.
The server has a significant gap in its tool surface; it only provides search functionality without any way to refine, save, or manage results. For a search domain, this is incomplete and will likely cause agent failures in complex tasks.