MCP.so
ログイン

Schemabrain

@Arun-kc

Schemabrain について

A read-only trust + intelligence layer between AI agents and your database — the agent never writes SQL, PII is refused before the query runs, and every call lands in a tamper-evident audit log. Postgres today.

基本情報

カテゴリ

データベース

トランスポート

stdio

公開者

Arun-kc

投稿者

arunkc

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "schemabrain": {
      "command": "uvx",
      "args": [
        "schemabrain",
        "serve",
        "--url-env",
        "DATABASE_URL"
      ],
      "env": {
        "DATABASE_URL": "postgresql://user:password@localhost:5432/dbname"
      }
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Schemabrain?

Schemabrain is an MCP server that acts as a read-only trust and intelligence layer between AI agents (Claude, Cursor, Windsurf) and your SQL database. It compiles SQL from definitions you control and refuses queries touching blocked categories before the database is queried.

How to use Schemabrain?

Install Schemabrain using the uvx package manager. It sits between an AI agent and a Postgres database. Twelve read-only MCP tools are available; the agent never writes SQL directly.

Key features of Schemabrain

  • Read-only architecture — 12 MCP tools, none can write.
  • PII-aware refusal — blocked-category queries are rejected before hitting the database.
  • Tamper-evident audit — SHA-256‑chained append‑only log of every call, refusal, and recovery.
  • Postgres support today; Apache‑2.0 licensed.
  • Simple installation via uvx.

Use cases of Schemabrain

  • Letting AI agents query a production database without risk of writes.
  • Preventing accidental or malicious PII extraction from the database.
  • Maintaining an immutable, verifiable audit trail of all agent queries.
  • Enforcing data-access policies through category-based refusal rules.

FAQ from Schemabrain

Is Schemabrain read-only?

Yes. All 12 MCP tools are read-only by architecture. The agent never writes SQL; SchemaBrain compiles SQL from definitions you control.

How does Schemabrain handle PII?

It maintains a set of blocked categories. Any query touching a blocked category is refused before the database is queried.

What database does Schemabrain support?

Currently only Postgres.

Is there an audit log?

Yes. Every call, refusal, and recovery is recorded in a SHA-256-chained append-only log that is tamper-evident.

How do I install Schemabrain?

Install using uvx.

コメント

「データベース」の他のコンテンツ