What it does
The publisher describes this MCP server as a secure SQL proxy for AI agents. According to its description, it translates natural language into SQL, applies AST-based safety checks to the generated queries, enforces row-level security separately for each agent, and records an audit log.
It fits projects where AI agents need to query a database and the team wants access rules and a record of activity between the agent and the data. The source does not describe supported databases, client setup or deployment steps.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.bch1212/queryshield
Secure SQL proxy for AI agents — NL→SQL, AST safety, per-agent RLS, audit log.
v1.0.1As shown on registry.modelcontextprotocol.io when we last read it