Fetch
- other
0
GitHub Stars
other
Language
5 months ago
First Indexed
2 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": {
"akm-2018-tmp_fetch": {
"command": "uvx",
"args": [
"mcp-server-fetch"
]
}
}
}You can use the MCP Fetch server to retrieve and convert web page content into a readable form for your models. This server handles web content by fetching a URL and rendering the HTML as markdown, which makes it easier to process and analyze web sources. Use it to chunk long pages, so your models can read content in manageable segments.
How to use
To use the Fetch MCP server, call the fetch tool via your MCP client. You provide the target URL and optional parameters to control length and starting point. These controls let you read large pages in chunks and extract just the information you need.
Tool options you can leverage include:
Practical usage patterns
-
Fetch a page and convert it to markdown for easier parsing by an LLM. Then ask to extract specific data from the markdown output.
-
Read a lengthy article in sequential chunks by incrementing start_index until you locate the required information.
Available tools
fetch
Fetches a URL from the internet and extracts its contents as markdown. Supports options to limit length, start from a specific index, and return raw content if requested.
