Kagi MCP Local
A Kagi search MCP server tool implemented in a local browser, providing an alternative to manual search
rating : 2 points
downloads : 12
What is Kagi MCP Local Server?
Kagi MCP Local Server is a local tool for directly accessing the Kagi search engine through your browser. It helps you quickly search the web and get results.How to use Kagi MCP Local Server?
First, install the required dependencies, then set up the server according to the provided configuration steps. After that, you can easily search through your browser.Use cases
This tool is suitable for users who need to use the Kagi search engine frequently and want to reduce manual operations. For example, researchers, students, or anyone who needs efficient searching.Main features
Local searchAchieve faster search response through the local server.
Customize the number of resultsAllow users to set the number of result entries returned for each search.
Support multiple browsersCompatible with mainstream browsers such as Chrome, Firefox, etc.
Advantages and limitations
Advantages
Improve search efficiency and reduce waiting time.
Protect privacy, and data will not leave the local environment.
Limitations
Need to install specific dependencies (such as uv).
May not support all advanced search functions.
How to use
Install dependencies
Make sure the uv tool is installed. You can get the installation guide from the official documentation.
Configure the server
Edit the configuration file to specify the browser path and other parameters.
Start the server
Run the command to start the MCP server.
Usage examples
Search for a keywordEnter the keyword 'Artificial Intelligence' to perform a search.
Batch searchSearch for multiple keywords at once and save the results.
Frequently Asked Questions
Can it be integrated with other search engines?
How to solve the problem of failed dependency installation?
Related resources
Kagi MCP Local GitHub
Project source code and documentation.
UV tool installation guide
Installation instructions for the UV tool.
Kagi MCP official server
Official Kagi MCP server.
Featured MCP Services

Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
131
4.5 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
824
4.3 points

Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
80
4.3 points

Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
1.7K
5 points

Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
555
5 points

Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
6.6K
4.5 points

Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
279
4.5 points

Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
746
4.8 points