What databases does Database Gateway support?
It supports PostgreSQL, MySQL, ClickHouse, Snowflake, Microsoft SQL Server, BigQuery, Oracle Database, SQLite, and ElasticSearch.
@centralmind
Basic information
Universal MCP-Server for your Databases optimized for LLMs and AI-Agents.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"gateway": {
"command": "docker",
"args": [
"run",
"--platform",
"linux/amd64",
"-p",
"9090:9090",
"\\"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
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.
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.
It supports PostgreSQL, MySQL, ClickHouse, Snowflake, Microsoft SQL Server, BigQuery, Oracle Database, SQLite, and ElasticSearch.
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.
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.
Yes. It supports local and on-premises deployment via standalone binary, Docker, or Kubernetes, and works with self-hosted LLMs through configurable AI endpoints.
Yes. It automatically generates Swagger UI documentation and an OpenAPI 3.1.0 specification for all created endpoints.
An official Qdrant Model Context Protocol (MCP) server implementation
MCP server for interacting with Neon Management API and databases
The Xata MCP server lets AI assistants and agents interact with your Xata organizations, projects, and Postgres database branches.

Model Context Protocol Servers
Postgres MCP Pro provides configurable read/write access and performance analysis for you and your AI agents.
Comments