Nexon33 Search Fetch Server MCP
An MCP server based on TypeScript, implementing a simple note system, providing resource management, tool operation, and prompt generation functions, and supporting integration with Claude Desktop.
rating : 2 points
downloads : 22
What is search-fetch-server?
This is an MCP protocol server developed based on TypeScript, implementing a simple note system. It accesses note resources through URIs and provides functions such as web page fetching, searching, and note summary generation.How to use search-fetch-server?
After connecting to the server through clients such as Claude Desktop, you can use functions like note creation, web page fetching, and searching. You need to add server information to the configuration file first.Applicable scenarios
Suitable for scenarios where you need to quickly record and organize information, or fetch content from web pages for summarization. Researchers, students, and knowledge workers will particularly benefit.Main features
Note systemAccess and manage text notes through note:// URIs. Each note contains a title, content, and metadata.
Create notesUse the create_note tool to create new notes. You need to provide the title and content parameters.
Web page fetchingThe fetch_url tool can obtain content from a specified URL, supporting both ordinary fetching and using Puppeteer to obtain fully rendered content.
Search functionThe duckduckgo_search tool can perform a DuckDuckGo search and return results in JSON format.
Note summaryThe summarize_notes prompt can generate a structured summary of all stored notes.
Advantages and limitations
Advantages
A lightweight and easy-to-deploy note system
Supports directly fetching content from web pages and converting it into notes
Integrated with DuckDuckGo search for convenient information retrieval
Provides a note summary function to help organize large amounts of information
Limitations
Currently only supports text notes, no rich text format
The Puppeteer fetching function requires additional dependencies and may have performance overhead
Notes are stored in the current session and there is no persistent storage
Requires technical knowledge for initial setup and configuration
How to use
Install dependencies
Ensure that the Node.js environment is installed, then run npm install to install the required dependencies.
Build the server
Use the build command to compile the TypeScript code.
Configure the client
Add server information to the Claude Desktop configuration file, specifying the startup command and path.
Start the server
You can directly run the compiled code or use the watch command for development mode.
Usage examples
Research material collectionQuickly collect web page content and save it as notes for subsequent research.
Meeting minutes organizationGenerate a summary after creating multiple meeting notes.
Information retrievalSearch for relevant information and directly save the results.
Frequently Asked Questions
Where is the note data stored?
What's the difference between Puppeteer fetching and ordinary fetching?
How to debug server issues?
Which clients are supported?
Related resources
MCP protocol documentation
Official documentation for the Model Context Protocol
MCP Inspector tool
A visualization tool for debugging MCP servers
Node.js official website
The Node.js environment required to run the server
Example configuration file
A complete example of the Claude Desktop configuration
Featured MCP Services

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
124
4.3 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
865
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
1.8K
5 points

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
176
4.5 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#
594
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
6.7K
4.5 points

Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
5.3K
4.7 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
313
4.5 points