Vericto SQL Firewall is answering right now. Last checked 14 min ago.
Check SQL against your Vericto rules before it runs: blocks destructive or risky statements.
Today is the operative word: we check Vericto SQL Firewall every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 14 min ago.
claude mcp add sql-firewall --transport http https://mcp.vericto.com/mcp
{
"mcpServers": {
"sql-firewall": {
"url": "https://mcp.vericto.com/mcp"
}
}
}
[mcp_servers.sql-firewall]
url = "https://mcp.vericto.com/mcp"
{
"mcpServers": {
"sql-firewall": {
"url": "https://mcp.vericto.com/mcp"
}
}
}
{
"mcpServers": {
"sql-firewall": {
"url": "https://mcp.vericto.com/mcp"
}
}
}
This endpoint answered with an authorization challenge. The server is running, but it did not say what kind of credentials it expects.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mcp.vericto.com/mcp | streamable-http | needs auth | 462 ms | 14 min ago |
Deterministic safety, correctness & cost gate that vets Postgres SQL before your AI agent runs it.
Governs what AI agents do: tool calls, SQL, commands, files checked against policy before they run.
ClickHouse query & management for AI agents — SQL-classified read/write/destructive gating.
App hosting your agent runs: git, deploys, staging/production, Postgres. Owner approves risky steps.
An Oracle MCP server built from the PL/SQL, tables and statements you select. No run-sql tool
Guardrail for AI agents on SQL Server: statement blocking, optional read-only mode and an audit log.
MCP server for SurrealDB: version check, SQL queries. Works with any instance.
Flipside Crypto SQL API: run queries, check status, fetch results.
Answers built from our own checks of this server.