awslabs.aurora-dsql-mcp-server
Level ALocalAn AWS Labs Model Context Protocol (MCP) server for Aurora DSQL
Overview
An AWS Labs MCP server for Aurora DSQL that converts natural-language questions into Postgres-compatible SQL and runs them against your DSQL cluster. Read-only by default, with writes enabled via --allow-writes. It reuses connections, retrieves table schemas, validates SQL for DSQL compatibility with optional auto-fix, and provides DSQL documentation search, reading, and best-practice recommendations.
Installation
MCP client config (paste into mcp.json)
{
"mcpServers": {
"awslabs-mcp-src-aurora-dsql-mcp-server": {
"command": "uvx",
"args": [
"awslabs.aurora-dsql-mcp-server@latest"
],
"env": {
"FASTMCP_LOG_LEVEL": "ERROR",
"AWS_REGION": "us-east-1"
}
}
}
}Agent install prompt
Copy and paste into Cursor / Claude / other agents to install this MCP for you
Please read this MCP repository and install it into my current environment:
https://github.com/awslabs/mcp/tree/main/src/aurora-dsql-mcp-server
Known working client config (can write into mcp.json):
{
"mcpServers": {
"awslabs-mcp-src-aurora-dsql-mcp-server": {
"command": "uvx",
"args": [
"awslabs.aurora-dsql-mcp-server@latest"
],
"env": {
"FASTMCP_LOG_LEVEL": "ERROR",
"AWS_REGION": "us-east-1"
}
}
}
}
Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.
Related servers
awslabs.amazon-bedrock-agentcore-mcp-serverModel Context Protocol (MCP) server for Amazon Bedrock AgentCore servicesawslabs.amazon-kendra-index-mcp-serverAn AWS Labs Model Context Protocol (MCP) server for amazon-kendra-index-mcp-servmempalaceThe best-benchmarked open-source AI memory system. And it's free.private-gptComplete API layer for private AI applications on local models: RAG, skills, toocodebase-memory-mcpLocal code intelligence for developers and AI agents. Connect code, docs and infcontext-modeFree, local plugin that keeps tool output out of your coding agent's context win