MCP.so
登录

Database Gateway

@centralmind

关于 Database Gateway

Universal MCP-Server for your Databases optimized for LLMs and AI-Agents.

基本信息

分类

数据库

许可证

Apache-2.0

运行时

go

传输方式

stdio

发布者

centralmind

提交者

Victor

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "gateway": {
      "command": "docker",
      "args": [
        "run",
        "--platform",
        "linux/amd64",
        "-p",
        "9090:9090",
        "\\"
      ]
    }
  }
}

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Database Gateway?

Database Gateway (CentralMind Gateway) is a tool that exposes your database to AI agents via the Model Context Protocol (MCP) or OpenAPI 3.1 protocols. It automatically generates secure, LLM-optimized APIs for structured data, making it easy for AI applications to query and interact with databases.

How to use Database Gateway?

Use Docker to run the gateway with a database connection string, or download the binary and run gateway start --config gateway.yaml. For initial API generation, run gateway discover with an AI provider (e.g., Gemini) and a connection string, then use the generated YAML configuration to start the server.

Key features of Database Gateway

  • Automatic API generation using LLMs based on table schema and sampled data
  • Supports PostgreSQL, MySQL, ClickHouse, Snowflake, MSSQL, BigQuery, Oracle, SQLite, ElasticSearch
  • Provides APIs as REST or MCP Server including SSE mode
  • Built-in authentication with API keys and OAuth
  • PII protection via regex or Microsoft Presidio plugin
  • Comprehensive monitoring with OpenTelemetry integration
  • Supports self-hosted LLMs and multiple AI providers (OpenAI, Anthropic, Bedrock, Gemini, VertexAI)
  • Row-level security via Lua scripts and LRU/time-based caching

Use cases of Database Gateway

  • Enable AI agents to query, create, or adjust data in your database during development
  • Chat with your database or data warehouse for analytical scenarios
  • Enrich AI applications like LangChain, OpenAI, Claude Desktop, and Cursor with live database data

FAQ from Database Gateway

What databases does Database Gateway support?

It supports PostgreSQL, MySQL, ClickHouse, Snowflake, Microsoft SQL Server, BigQuery, Oracle Database, SQLite, and ElasticSearch.

How do I get started with Database Gateway?

Install via Docker or binary, connect to your database, run the discover command with an AI provider and your connection string, then start the server with the generated YAML configuration.

Does Database Gateway support authentication and security?

Yes. It has built-in API key and OAuth authentication, PII redaction plugins, row-level security via Lua scripts, and monitoring through OpenTelemetry for audit trails.

Can I run Database Gateway locally or on-premises?

Yes. It supports local and on-premises deployment via standalone binary, Docker, or Kubernetes, and works with self-hosted LLMs through configurable AI endpoints.

Does Database Gateway provide API documentation?

Yes. It automatically generates Swagger UI documentation and an OpenAPI 3.1.0 specification for all created endpoints.

评论

数据库 分类下的更多 MCP 服务器