Vericto: database guardrails for AI agents
com.verictoPublished by vericto.comOfficial publisherv1.1.0Updated Nov 1, 2026
Database guardrails for AI agents: check SQL against your Vericto rules before it runs.
The publisher's own server: Vericto SQL Firewall
Overview
Vericto checks SQL against your Vericto guardrail rules before it runs, giving AI agents a pre-execution safety check on database queries.
- What you can do
- Check SQL statements against your Vericto rules before they are executed.
- Run the check through a dry-run execution scope, so queries are validated rather than applied.
- Report rule outcomes back to the assistant so it can adjust a query before running it.
- No tool list is published, so the exact operations are not documented in the supplied material.
- When to use it
- Use it when an assistant writes or runs SQL against real databases and you want queries validated against organizational rules first. It suits teams that already maintain Vericto guardrail policies and want agents to respect them.
- Requirements
- A remote MCP endpoint at mcp.vericto.com over streamable HTTP. OAuth authentication is required, plus a Vericto API key sent in the X-API-Key header; the key must carry only the ci_dryrun:execute scope and is created in the Vericto dashboard under API Keys. A Vericto account with configured rules is implied.
Installation
In SourceWeft
- Open Vericto: database guardrails for AI agents in the dashboard and add it to a workspace.
- Connect the required credentials. They are stored privately and never shown on public pages.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/com.vericto%2Fmcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.
{
"mcpServers": {
"vericto-database-guardrails-for-ai-agent": {
"type": "http",
"url": "https://mcp.vericto.com/mcp"
}
}
}Tools
0Version history
1- v1.1.0LatestNov 1, 2026
Score
83% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
- Auth declaredRequired10 pts
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- LicenseNot applicable
A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.
Other Vericto integrations
Vericto SQL Firewall
com.verictoOfficial publisher
Vericto SQL Firewall checks SQL statements against your Vericto rules before they run, blocking destructive or risky queries.
Vericto account (OAuth)
com.verictoOfficial publisher
Remote Vericto workspace server over OAuth that lets an assistant check setup status, rules, CI reports, docs search and SQL checks.
Vericto Proxy mode (local, PostgreSQL)
com.vericto
Vericto Proxy mode (local, PostgreSQL)'s local MCP server, published by vericto.com; no sign-in required; STDIO.