> ## Documentation Index
> Fetch the complete documentation index at: https://docs.querybear.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> QueryBear is a secure, read-only MCP server that connects AI assistants like Claude, Cursor, and ChatGPT to your production PostgreSQL, MySQL, and SQLite databases.

QueryBear is a managed **MCP (Model Context Protocol) server** that gives AI assistants safe, read-only access to your databases. Drop the QueryBear MCP endpoint into Claude Code, Cursor, ChatGPT, Codex, Windsurf, or Claude Desktop, and your agent can answer questions like *"how many users signed up last week?"* by writing a real SQL query against your real database — without you giving it the ability to break anything.

## The problem

AI agents are useful only when they can see your data. But pointing them at your production database directly is a disaster waiting to happen:

* A misbehaving agent could run `DROP TABLE users` and you'd find out at 3am.
* A prompt-injected agent could `SELECT * FROM api_keys` and exfiltrate secrets.
* A naive agent could `SELECT *` from your 800-million-row events table and DoS your read replica.
* A non-technical user has no way to audit what queries the agent actually ran.

The standard advice — "just use a read-only Postgres role" — solves the first problem and none of the others. Read-only roles can still read every column, run unbounded scans, and don't help you when the agent itself is being manipulated.

## What QueryBear does

QueryBear sits between the agent and your database as a hardened SQL gateway:

<CardGroup>
  <Card title="SQL parser enforces read-only">
    Every query is parsed before execution. `INSERT`, `UPDATE`, `DELETE`, and all DDL are rejected at the gateway — not just by the database role.
  </Card>

  <Card title="Allow-listed tables">
    Only tables you opt in are visible to the agent. Everything else is invisible in schema responses and rejected if queried.
  </Card>

  <Card title="Blocked columns">
    Mark sensitive columns (passwords, tokens, PII) once. They're stripped from schema results and any query referencing them is rejected.
  </Card>

  <Card title="Row limits and timeouts">
    Every query gets an enforced `LIMIT` and a wall-clock timeout. The agent can't accidentally pull millions of rows or run a 10-minute scan.
  </Card>

  <Card title="Full audit log">
    Every query, every schema fetch, every connection — logged with timestamp and originating client. Available in the dashboard.
  </Card>

  <Card title="Works with any MCP client">
    Claude Code, Claude Desktop, Cursor, Codex, Windsurf, and ChatGPT all supported with one-line config.
  </Card>
</CardGroup>

## Supported databases

* [PostgreSQL](/databases/postgres) — 12+
* [MySQL](/databases/mysql) — 5.7+ and MariaDB
* [SQLite](/databases/sqlite) — local file access

## Supported AI clients

* [Claude Code](/clients/claude-code)
* [Claude Desktop](/clients/claude-desktop)
* [Cursor](/clients/cursor)
* [Codex](/clients/codex)
* [Windsurf](/clients/windsurf)
* [ChatGPT](/clients/chatgpt)

## Next steps

<CardGroup>
  <Card title="Quickstart" href="/quickstart">
    Connect your first database and wire up an AI client in 5 minutes.
  </Card>

  <Card title="What is MCP?" href="/what-is-mcp">
    New to Model Context Protocol? Start here.
  </Card>

  <Card title="Security model" href="/features/security">
    The full defense-in-depth model and threat assumptions.
  </Card>

  <Card title="Setup guides" href="/guides/postgres-claude-code">
    Step-by-step guides for every database × AI client combination.
  </Card>
</CardGroup>