gateway

<div align="center">

![Build Binaries](https://github.com/centralmind/gateway/actions/workflows/build-binaries.yml/badge.svg) &nbsp; <a href="https://discord.gg/XFhaUG4F5x"><img src="https://dcbadge.limes.pink/api/server/https://discord.gg/XFhaUG4F5x" height="20"></a> &nbsp;&nbsp;<a href="https://t.me/+TM3T1SikjzA4ZWVi"><img src="https://img.shields.io/badge/telegram-%E2%9D%A4%EF%B8%8F-252850?style=plastic&logo=telegram" height=20></a> &nbsp;&nbsp; <a href="https://docs.centralmind.ai"><img src="https://img.shields.io/badge/Full%20Documentation-blue?style=for-the-badge&logo=rocket&logoColor=white" height="20"></a>

</div>

<h2 align="center">CentralMind Gateway: Create API or MCP Server in Minutes</h2>

🚀 Interactive Demo via GitHub Codespaces

[![Deploy with GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/centralmind/sample_databases)

## What is Centralmind/Gateway

CentralMind Gateway simplifies exposing databases to AI Agents via MCP or OpenAPI. It automatically generates AI-optimized APIs, addressing the need for fast and secure data access for LLM-powered applications. A simple Docker command can launch an API with Swagger UI and an MCP SSE server.

## Why Centralmind/Gateway

It filters PII, adds auditing, and optimizes for AI workloads, supporting Model Context Protocol (MCP). It caters to companies deploying AI agents for customer support and analytics, eliminating direct SQL access to databases, mitigating security, compliance, and performance risks.

## Features

Key features include automatic API generation, support for databases like PostgreSQL, MySQL, ClickHouse, and Snowflake. It offers REST and MCP protocols, auto-generated Swagger documentation, PII protection via plugins, flexible YAML configuration, and Helm chart deployment. It supports OpenAI, Anthropic, Amazon Bedrock, Google Gemini, and VertexAI, self-hosted LLMs, row-level security, API keys, OAuth, OpenTelemetry integration, and LRU caching.

## How it Works

Gateway connects to databases, analyzes schemas, and generates APIs using LLMs. It supports Docker and Kubernetes deployments. Access data via REST or MCP, integrating with LangChain, OpenAI, and Claude.

## Documentation

Links to quickstart, installation, API generation, API launch, ChatGPT integration, database connectors, and plugin documentation.

## How to Build

Instructions for cloning the repository, installing dependencies, and building the project.

## API Generation

Details on using AI providers like Google Gemini (with free tier via Google AI Studio) to generate API configurations.

## Running the API

Instructions for running the API locally or using Docker Compose.

## MCP Protocol Integration

Instructions for integrating with Claude Desktop using the MCP protocol.

## Roadmap

Future features include extended database integrations (Redshift, S3, Oracle, MSSQL, Elasticsearch), SSH tunneling, advanced query capabilities, enhanced MCP security, schema management, traffic management, and write operations support.