Gateway is listed as active in the registry but did not answer our last check. 43 installs a week from npm.
Governed MCP gateway: approval gates, signed audit receipts, and cost control for agent tool calls.
Gateway 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 4 min ago.
claude mcp add gateway --transport http https://api.blacklake.systems/mcphttps://api.blacklake.systems/mcp[mcp_servers.gateway]
url = "https://api.blacklake.systems/mcp"{
"mcpServers": {
"gateway": {
"url": "https://api.blacklake.systems/mcp"
}
}
}{
"servers": {
"gateway": {
"type": "http",
"url": "https://api.blacklake.systems/mcp"
}
}
}Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://api.blacklake.systems/mcp | streamable-http | answering | 261 ms | 4 min ago |
Alternatives to Gateway
same job, measured the same wayGoverned MCP front door to FLOCORE; write calls need human approval and signed receipts.
Gate for coding agents' MCP and built-in tool calls: rules, approvals and hash-chained receipts
Policy-based governance for AI agent tool calls. YAML policy, approval gates, audit logging.
Governed MCP gateway: approved tools only, each call policy-checked and recorded per agent
Budget, payment and audit controls for AI agent API calls and MCP tool calls.
Governed AI workflows with human approval gates and audit trails for Claude and MCP clients.
MCP gateway that checks each agent tool call against a signed grant and policy, and signs a receipt
Verifiable decision records for AI agents: signed receipts for calls to its own governed tools.
Gateway — questions
Answers built from our own checks of this server.