Approval Gate MCP runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 15 Oct 2026.
Fail-closed human approval gates for AI agent actions. Default-deny, TTL expiry, audit log.
Today is the operative word: we check Approval Gate 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 approval-gate-mcp -- npx -y @itcustomsolution/approval-gate-mcp
{
"mcpServers": {
"approval-gate-mcp": {
"args": [
"-y",
"@itcustomsolution/approval-gate-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.approval-gate-mcp]
command = "npx"
args = ["-y", "@itcustomsolution/approval-gate-mcp"]
{
"mcpServers": {
"approval-gate-mcp": {
"args": [
"-y",
"@itcustomsolution/approval-gate-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"approval-gate-mcp": {
"args": [
"-y",
"@itcustomsolution/approval-gate-mcp"
],
"command": "npx"
}
}
}
Pre-execution gate for AI-agent tool calls. Touch ID approval. Tamper-evident audit log.
Gate an AI agent's destructive actions behind human approval, with a tamper-evident log.
Runtime authority for AI agents: credential mediation, spend cap, approval gates, audit log.
Policy-based governance for AI agent tool calls. YAML policy, approval gates, audit logging.
Hosted CRM and email desk for AI agents: key per agent, audit log, one-click undo, opt-in approval.
Human approvals, autonomy limits and a chained audit log for the AI agents of service firms.
Audit trail and traceability for AI agents. MCP gate: evaluate, ingest, request approval.
Bitcoin-anchored, tamper-evident audit log for AI agents — record, disclose and verify actions.
Answers built from our own checks of this server.