Database Intelligence Layer MCP Server

@terno-ai

リポジトリ

基本情報

カテゴリ

データベース

トランスポート

stdio

作者

terno-ai

投稿者

Navin Kumar

Database Intelligence Layer MCP Server について

TernoDBI is a database intelligence layer designed for Security and Accuracy, bridging the gap between AI Agents and Enterprise Data. It acts as a powerful standalone Model Context Protocol (MCP) server, or it can be directly embedded into your existing Django projects. Either wa

#security#accuracy

Database Intelligence Layer MCP Server の設定

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": {
    "ternodbi-query": {
      "command": "uvx",
      "args": [
        "--from",
        "terno-dbi",
        "dbi-mcp",
        "query"
      ],
      "env": {
        "TERNODBI_API_URL": "http://127.0.0.1:8376",
        "TERNODBI_API_KEY": "dbi_query_YOUR_TOKEN_HERE"
      }
    },
    "ternodbi-admin": {
      "command": "uvx",
      "args": [
        "--from",
        "terno-dbi",
        "dbi-mcp",
        "admin"
      ],
      "env": {
        "TERNODBI_API_URL": "http://127.0.0.1:8376",
        "TERNODBI_API_KEY": "dbi_admin_YOUR_TOKEN_HERE"
      }
    }
  }
}

Database Intelligence Layer MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is Database Intelligence Layer?

TernoDBI (the Database Intelligence Layer) is an MCP server that bridges AI agents and enterprise databases. It provides a secure, unified API for warehouse-scale databases while enforcing row-level security, schema enrichment, and multi-database support.

How to use Database Intelligence Layer?

Install via pip install terno-dbi, run ternodbi start, configure datasources in the admin panel, generate an access token with the CLI (ternodbi manage issue_token), then connect MCP clients like Claude Desktop using the provided JSON configuration. The server runs on 127.0.0.1:8376.

Key features of Database Intelligence Layer

Multi-database support: Postgres, MySQL, Snowflake, BigQuery, Databricks, Oracle, SQLite
Split MCP architecture: Query Server (read-only) and Admin Server (write/management)
Enterprise-grade security: Row-Level Security, Privacy-by-Default, SQLShield AST validation
LLM-ready schema enrichment with semantic metadata and statistical profiling
High-performance cursor-based pagination (HMAC) with ~28x speedup
Direct integration into existing Django projects as an embedded app

Use cases of Database Intelligence Layer

Secure querying of enterprise databases by AI assistants with granular access control
Enabling natural-language database exploration via Claude Desktop
Embedding into custom AI agent workflows (LangChain, LlamaIndex) using REST APIs
Adding intelligence to existing Django web applications through direct app integration

よくある質問

What databases does Database Intelligence Layer support?

It supports Postgres, MySQL, Snowflake, BigQuery, Databricks, Oracle, and SQLite.

How does Database Intelligence Layer ensure security?

It provides Row-Level Security (SQL-based filters), privacy-by-default hiding of sensitive columns and tables, and SQLShield AST-based validation to prevent SQL injection and destructive operations.

Can Database Intelligence Layer be integrated into existing Django projects?

Yes, add `terno-dbi` to your environment, include `'terno_dbi.core'` in `INSTALLED_APPS`, mount its URLs, and run migrations. Then use its models and services programmatically.

What are the runtime requirements?

Python 3.10+ and Django 4.2+ are required. The server runs locally on `127.0.0.1:8376`.

How do I generate access tokens?

Use the CLI: `ternodbi manage issue_token --name "Agent Name" --type query` (or `admin` for admin tokens). Tokens can be scoped to a specific datasource and can have expiration dates.