- Home
- MCP servers
- Search Fetch
Search Fetch
- typescript
0
GitHub Stars
typescript
Language
7 months ago
First Indexed
3 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"mcp-mirror-nexon33_search-fetch-server-mcp": {
"command": "node",
"args": [
"/path/to/search-fetch-server/build/index.js"
]
}
}
}You can run a lightweight MCP server that manages text notes, fetches content from URLs, and performs searches. It exposes resources for notes, tools to create and fetch notes, and prompts to generate summaries, making it practical for building note-centric assistants or test clients against the MCP protocol.
How to use
Interact with the server through an MCP client to access and manage notes, fetch web content, and perform searches. You can create new notes, retrieve existing ones via note:// URIs, and request summaries of all stored notes using the summarize_notes prompt. Use the tools to create notes, fetch external URLs (with optional Puppeteer-based conversion to markdown), and run DuckDuckGo searches. Prompts can generate structured summaries that include all note contents as embedded resources, ready for an LLM workflow.
How to install
Prerequisites you need on your development machine:
- Node.js and npm installed (Node.js 14+ is typical for MCP servers)
- A working Git client
- A supported shell environment
Install dependencies and build the server from source:
npm install
npm run build
Additional configuration and run notes
To run via the Claude Desktop integration, configure the MCP server in Claude’s desktop config. The example below wires the server as a local stdio process:
{
"mcpServers": {
"search_fetch_server": {
"command": "node",
"args": ["/path/to/search-fetch-server/build/index.js"]
}
}
}
Available tools
create_note
Create a new text note by providing a title and content; the note is stored in the server state.
fetch_url
Fetch content from a URL and optionally convert it to markdown using Puppeteer. If use_puppeteer is true, waitUntil is set to networkidle2 with a 30-second timeout; otherwise, use axios and return content as-is.
duckduckgo_search
Perform a DuckDuckGo search and return the results as a JSON string.
summarize_notes
Generate a structured summary of all stored notes, including all note contents as embedded resources, suitable for an LLM.