mcpField
S
search-fetch-server MCP Server

search-fetch-server MCP Server

Local
github.com/nexon33Search0Updated 97w ago

About search-fetch-server MCP Server

search-fetch-server MCP Server is a TypeScript notes and web-retrieval MCP server for users who want to store and summarize text through an MCP client. It can also fetch URL content and search DuckDuckGo.

Key features

  1. 01Create and store text notes
  2. 02Access notes as URI resources
  3. 03Fetch pages with optional Markdown conversion
  4. 04Search DuckDuckGo
  5. 05Provide a note-summary prompt

Use cases

  1. 01Save text notes during research
  2. 02Retrieve and read webpage content
  3. 03Search topics and obtain results
  4. 04Summarize saved notes with an LLM

MCP support

It exposes note resources, note-creation and web-retrieval tools, and a prompt for summarizing notes to MCP clients.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

search-fetch-server MCP Server

A Model Context Protocol server

This is a TypeScript-based MCP server that implements a simple notes system. It demonstrates core MCP concepts by providing:

  • Resources representing text notes with URIs and metadata
  • Tools for creating new notes, fetching URLs, and performing searches
  • Prompts for generating summaries of notes

Features

Resources
  • List and access notes via note:// URIs
  • Each note has a title, content and metadata
  • Plain text mime type for simple content access
Tools
  • create_note - Create new text notes
    • Takes title and content as required parameters
    • Stores note in server state
  • fetch_url - Fetch content from a URL and optionally convert to markdown using Puppeteer
    • Takes a URL as a required parameter
    • Takes an optional use_puppeteer boolean parameter. If true, it will use puppeteer with waitUntil set to networkidle2 and a timeout of 30 seconds. Otherwise, it will use axios.
    • Returns the content of the URL as markdown if using puppeteer, otherwise returns the content as is.
  • duckduckgo_search - Perform a DuckDuckGo search
    • Takes a query as a required parameter
    • Returns search results as a JSON string
Prompts
  • summarize_notes - Generate a summary of all stored notes
    • Includes all note contents as embedded resources
    • Returns structured prompt for LLM summarization

Development

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

Installation

To use with Claude Desktop, add the server config:

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "search-fetch-server": {
      "command": "node",
      "args": ["/path/to/search-fetch-server/build/index.js"]
    }
  }
}
Debugging

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:

npm run inspector

The Inspector will provide a URL to access debugging tools in your browser.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.