SchemaBrain is an MCP server that sits between AI agents (Claude, Cursor, Windsurf) and your SQL database as a read-only trust + intelligence layer. The agent never writes SQL — 12 tools compile it from definitions you control, PII and secret categories are refused before the query runs, and every call lands in a tamper-evident (SHA-256-chained) audit log. Postgres today.
A default-deny SQL firewall sidecar for AI agents that enforces per-agent policies on database queries, provides safe rewrites, and maintains a tamper-evident audit chain.
Enables AI agents to execute SQL queries and introspect PostgreSQL schemas, tables, and indexes with read-only safety by default. Supports optional write operations and works with Claude, LangChain, and other agents via stdio or HTTP transports.
Connects AI assistants to PostgreSQL databases with production-grade safety features including query validation, guarded writes, rate limiting, and audit logging.