Approval Rules is listed as active in the registry but did not answer our last check. It exposes 6 tools.
Auto-approve small agent actions under your rules; approval cards for the rest.
Over the last week it answered 97.5% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 2 min ago.
claude mcp add approve --transport http https://approve.cloudforbots.com/mcp
{
"mcpServers": {
"approve": {
"url": "https://approve.cloudforbots.com/mcp"
}
}
}
[mcp_servers.approve]
url = "https://approve.cloudforbots.com/mcp"
{
"mcpServers": {
"approve": {
"url": "https://approve.cloudforbots.com/mcp"
}
}
}
{
"mcpServers": {
"approve": {
"url": "https://approve.cloudforbots.com/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
get_rules
set_rules
check_action
get_decision
usage_and_upgrade
weekly_report
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://approve.cloudforbots.com/mcp | streamable-http | answering | 28 ms | 2 min ago |
Set up human approval for your AI agents' tool calls.
Turn OpenAPI services into tools an agent can call under your rules.
Give your agents your team's real data — read the shared graph, propose actions your team approves.
Human approval for irreversible AI agent actions, bound to the exact tool call by a passkey tap
Notifications you can answer: agents push to your phone and wait for your approval or reply.
A local receipt and approval gate for AI agent sessions. The agent can act, but it cannot sign.
Human-in-the-loop approval for agent actions, with verifiable action-bound receipts.
Remembers why you approved, edited or rejected your agent's drafts; recalls the closest corrections
Answers built from our own checks of this server.