Undo MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 23 installs a week from npm.
Reversibility intelligence — check if actions can be undone before executing them.
Today is the operative word: we check Undo MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add undo-mcp -- npx -y @agentutil/undo-mcp
{
"mcpServers": {
"undo-mcp": {
"args": [
"-y",
"@agentutil/undo-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.undo-mcp]
command = "npx"
args = ["-y", "@agentutil/undo-mcp"]
{
"mcpServers": {
"undo-mcp": {
"args": [
"-y",
"@agentutil/undo-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"undo-mcp": {
"args": [
"-y",
"@agentutil/undo-mcp"
],
"command": "npx"
}
}
}
Consequence evaluation for AI agents. Check recoverability before destructive actions.
Naming engine with availability intelligence: score names, check domains, socials and registries.
SEO and AI-answer visibility intelligence for search, content gaps, and GEO actions.
Sonatype component intelligence: versions, security analysis, and Trust Score recommendations
Pre-execution audit for autonomous agents. Independent receipt before irreversible actions.
Live competitive intelligence for B2B teams — signals, threat rankings, and revenue-driving actions.
Check x402 endpoints before paying: liveness, price history, farm detection. Plus RU web access.
Authorize consequential AI agent actions before execution
Answers built from our own checks of this server.