{"type":"mcp_server","name":"gateway","description":"CentralMind Gateway simplifies exposing databases to AI agents via MCP or OpenAPI. It generates AI-optimized APIs, filters sensitive data for compliance, and provides fast, secure data access for LLM-powered applications.","category":"Communication","language":"Go","stars":528,"forks":12,"owner":"centralmind","github_url":"https://github.com/centralmind/gateway","homepage":"https://centralmind.ai","setup":"## Setup\n\n1.  Clone the repository: `git clone https://github.com/centralmind/gateway.git`\n2.  Navigate to project directory: `cd gateway`\n3.  Install dependencies: `go mod download`\n4.  Build the project: `go build .`\n\n**API Generation:**\n\n1.  Choose a supported AI provider (OpenAI, Anthropic, Amazon Bedrock, Google Vertex AI, Google Gemini).\n2.  Configure AI provider authorization (e.g., set `GEMINI_API_KEY='yourkey'` for Google Gemini).\n3.  Run the discovery command: `./gateway discover --ai-provider gemini --connection-string \"postgresql://neondb_owner:MY_PASSWORD@MY_HOST.neon.tech/neondb?sslmode=require\" --prompt \"Generate for me awesome readonly API\"`\n4.  Review the generated configuration in `gateway.yaml`.\n\n**Running the API:**\n\n1.  Run locally: `./gateway start --config gateway.yaml rest`\n2.  Docker Compose: `docker compose -f ./example/simple/docker-compose.yml up`\n\n**MCP Protocol Integration:**\n\n1.  Build the gateway binary: `go build .`\n2.  Configure Claude Desktop tool configuration with the path to the gateway binary and YAML config.","tools":"## Available Tools\n\n1.  **Automatic API Generation** (Creates APIs automatically using LLM based on table schema and sampled data)\n2.  **Structured Database Support** (Supports PostgreSQL, MySQL, ClickHouse, Snowflake, MSSQL, BigQuery, Oracle Database, SQLite, ElasticSearch)\n3.  **Multiple Protocol Support** (Provides APIs as REST or MCP Server including SSE mode)\n4.  **API Documentation** (Auto-generated Swagger documentation and OpenAPI 3.1.0 specification)\n5.  **PII Protection** (Implements regex plugin or Microsoft Presidio plugin for PII and sensitive data redaction)\n6.  **Flexible Configuration** (Easily extensible via YAML configuration and plugin system)\n7.  **Deployment Options** (Run as a binary or Docker container with ready-to-use Helm chart)\n8.  **Multiple AI Providers Support** (Support for OpenAI, Anthropic, Amazon Bedrock, Google Gemini & Google VertexAI)\n9.  **Local & On-Premises** (Support for self-hosted LLMs through configurable AI endpoints and models)\n10. **Row-Level Security (RLS)** (Fine-grained data access control using Lua scripts)\n11. **Authentication Options** (Built-in support for API keys and OAuth)\n12. **Comprehensive Monitoring** (Integration with OpenTelemetry (OTel) for request tracking and audit trails)\n13. **Performance Optimization** (Implements time-based and LRU caching strategies)","faq":null,"created_at":"2025-02-10T19:34:14+00:00","updated_at":"2025-03-28T19:02:39+00:00","source_url":"https://model-context-protocol.com/servers/ai-agent-database-gateway-llm-api","related_articles":[]}