Safetyreplay MCP is listed as active in the registry but did not answer our last check. Last commit 19 May 2026.
Paid remote MCP for safety replays, policy gates, eval receipts, and release evidence.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 7 min ago.
claude mcp add safetyreplay-mcp --transport http https://safetyreplay.clauxel.com/mcp
{
"mcpServers": {
"safetyreplay-mcp": {
"url": "https://safetyreplay.clauxel.com/mcp"
}
}
}
[mcp_servers.safetyreplay-mcp]
url = "https://safetyreplay.clauxel.com/mcp"
{
"mcpServers": {
"safetyreplay-mcp": {
"url": "https://safetyreplay.clauxel.com/mcp"
}
}
}
{
"mcpServers": {
"safetyreplay-mcp": {
"url": "https://safetyreplay.clauxel.com/mcp"
}
}
}
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://safetyreplay.clauxel.com/mcp | streamable-http | answering | 42 ms | 7 min ago |
Policy-gated x402 MCP for agent workflows with TEE receipts, 18 tools, and no custody.
Signed receipts and Cedar policies for AI agent tool calls. Claude Code hooks, MCP gateway.
Governed USDC wallet for AI agents — policy gates, spending caps, and Ed25519-signed receipts.
Remote MCP security gateway for auth, redaction, policy enforcement, and audit logging.
MCP server for LiveAuth: PoW + Lightning auth, L402 bundles, and paid MCP tool receipts.
Audit infrastructure for AI coding agents with evidence-backed review and policy gates.
The evidence layer for MCP: live operational grades plus Trust Receipts for every registry server.
Default trust layer for agentic payments: authorize agent spend, evidence, receipts, settlement.
Answers built from our own checks of this server.