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.
Safetyreplay MCP does not always answer
Over the last week it answered 0.0% of our checks. We check every 15 minutes, so you hear about the next outage within the hour — not from your users.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 12 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"
}
}
}Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://safetyreplay.clauxel.com/mcp | streamable-http | answering | 124 ms | 12 min ago |
Alternatives to Safetyreplay MCP
same job, measured the same wayRead-only evidence for the tools agents run: MCP server records, coverage and policy.
Mechanical write gates, evidence receipts, and adversarial review for AI coding agents.
Evidence-gated verification, selection, and measurement MCP for coding agents.
Policy-gated x402 MCP for agent workflows with TEE receipts, 18 tools, and no custody.
Agent leases, signed receipts, watchdogs, and optional paid source-verification evidence.
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.
Read-only verification evidence for paid machine services and buyer policy checks.
Safetyreplay MCP — questions
Answers built from our own checks of this server.