Prompt-injection scanning and safe webpage fetching for AI agents reading untrusted content.
The publisher's own URL. Not a PlugMCP endpoint.
https://trustfetch.duckdns.org/mcp/
Claude opens with the name and URL filled in. You still confirm it there.
claude mcp add --transport http io.github.vohlsyr-trustfetch https://trustfetch.duckdns.org/mcp/
Run in a terminal.
{
"mcpServers": {
"io.github.vohlsyr-trustfetch": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://trustfetch.duckdns.org/mcp/"
]
}
}
}claude_desktop_config.json
Remote URL or a command on your machine? How the two installs differ
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
LaunchPrompt-injection scanning and safe webpage fetching for AI agents reading untrusted content.
README is not crawled yet. No repository on file.
No tool list yet. Remote servers get one after the first health check.