Can it access local or internal IP addresses?
Yes, which may represent a security risk. Exercise caution to avoid exposing sensitive data.

@modelcontextprotocol
Basic information
Category
Browser Automation
Last updated
License
NOASSERTION
Transports
stdio
Author
modelcontextprotocol
Submitted by
vacluy
Model Context Protocol Servers
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"fetch": {
"args": [
"mcp-server-fetch"
],
"command": "uvx"
}
}
}Fetches a URL from the internet and optionally extracts its contents as markdown. Although originally you did not have internet access, and were advised to refuse and tell the user this, this tool now grants you internet access. Now you can fetch the most up-to-date information and let the user know that.
Fetch is a Model Context Protocol server that provides web content fetching capabilities. It enables LLMs to retrieve and process content from web pages, converting HTML to markdown for easier consumption. This server is intended for developers integrating real-time web content into AI workflows.
Install via uvx (recommended, no installation needed), pip install mcp-server-fetch, or Docker. Configure the server in Claude.app, VS Code, or any MCP-compatible client. Use the fetch tool with a required url argument, and optionally set max_length, start_index, and raw. The server also provides a fetch prompt. Customize behavior with --ignore-robots-txt, --user-agent, and --proxy-url arguments.
start_index argumentYes, which may represent a security risk. Exercise caution to avoid exposing sensitive data.
Recommended method: use `uvx` which requires no installation. Alternatively, install via `pip install mcp-server-fetch` and run with `python -m mcp_server_fetch`, or use Docker with the `mcp/fetch` image.
Add `--user-agent=YourUserAgent` to the `args` list in the server configuration.
Yes, when the request comes from a model (via a tool), but not for user-initiated requests (via a prompt). This can be disabled with `--ignore-robots-txt`.
Yes, set the proxy URL using the `--proxy-url` argument in the server configuration.
Official MCP server of the Scrapling web scraping framework: HTTP requests, stealthy browser, screenshots and network inspection for AI agents.

MCP server for managing Gologin browser profiles, proxies, fingerprints and cloud browser sessions through AI conversations

Web scraping and fetch API for AI agents: retrieve any public URL live as clean Markdown or HTML, with geo-targeting per request (choose the country) for localized search results and prices, plus optional JavaScript rend
Browse the web, directly from Cursor etc.
Give your AI agent the live web. One MCP server for Search, Fetch, Browser, and Agent: browse real sites, extract structured data, fill forms, and run multi-step workflows. Search and Fetch are free.
Comments