Loading
Verified AI-agent outcomes: secret scanning, JSON cleanup, dedupe, anomaly and schema checks.
The publisher's own URL. Not a PlugMCP endpoint.
https://humanmirror.fr/api/outcome/mcp/
Claude opens with the name and URL filled in. You still confirm it there.
claude mcp add --transport http fr.humanmirror-outcome https://humanmirror.fr/api/outcome/mcp/
Run in a terminal.
{
"mcpServers": {
"fr.humanmirror-outcome": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://humanmirror.fr/api/outcome/mcp/"
]
}
}
}claude_desktop_config.json
Remote URL or a command on your machine? How the two installs differ
Verified AI-agent outcomes: secret scanning, JSON cleanup, dedupe, anomaly and schema checks.
README is not crawled yet. Open the repository
No tool list yet. Remote servers get one after the first health check.