Loading
Human approvals, autonomy limits and a chained audit log for the AI agents of service firms.
The publisher's own URL. Not a PlugMCP endpoint.
https://app.ai-agents-pitstop.com/mcp/workspace/
Claude opens with the name and URL filled in. You still confirm it there.
claude mcp add --transport http com.ai-agents-pitstop-pitstop https://app.ai-agents-pitstop.com/mcp/workspace/
Run in a terminal.
{
"mcpServers": {
"com.ai-agents-pitstop-pitstop": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://app.ai-agents-pitstop.com/mcp/workspace/"
]
}
}
}claude_desktop_config.json
Remote URL or a command on your machine? How the two installs differ
Human approvals, autonomy limits and a chained audit log for the AI agents of service firms.
README is not crawled yet. No repository on file.
No tool list yet. Remote servers get one after the first health check.