Sold by: Tech 42
Deployed on AWS
Free Trial
Enable AI assistants to query and optimize PostgreSQL databases using natural language via a secure MCP server deployed on AWS ECS Fargate with credential isolation.
A production-grade Model Context Protocol (MCP) server for PostgreSQL that enables AI assistants to perform natural language SQL generation, schema inspection, query optimization, and database health diagnostics without exposing raw database credentials to client applications. Supports Admin and Tenant operating modes deployed on AWS ECS Fargate.
Overview
The Tech 42 PostgresSQL Text-to-SQL MCP Server lets AI assistants query, analyze, and optimize PostgreSQL databases using natural language, no SQL expertise required. Whether you're running AI agents with AWS Bedrock, building agentic workflows, or giving teams a safe database interface, this Model Context Protocol (MCP) server delivers schema discovery, text-to-SQL generation, query optimization, and database health monitoring out of the box.
Built for AWS, the server deploys as a container on Amazon ECS Fargate behind an Application Load Balancer, with credentials managed through AWS Secrets Manager. It connects to Amazon RDS and other PostgreSQL instances via VPC Peering, keeping all database traffic private. Two access modes: Admin for development and DBA workflows, and Tenant Mode for multi-tenant apps with row-level security (RLS); make it flexible for both internal tools and customer-facing applications.
Key capabilities include: natural language SQL, slow query analysis, index recommendations, workload analysis, hypothetical index planning with HypoPG, schema inspection, and comprehensive database health checks. Compatible with Claude, AWS Bedrock Agents, and any MCP-enabled AI agent framework.
Highlights
- AI-powered natural language SQL generation converts plain English into optimized PostgreSQL queries, eliminating the need for SQL expertise. Schema discovery, slow query analysis, index recommendations, and hypothetical index planning with HypoPG give teams comprehensive database intelligence through a single MCP interface - compatible with any MCP-enabled AI framework.
- Flexible access modes: Unrestricted for dev/DBA workflows, Restricted for read-only production diagnostics, and Tenant Mode for multi-tenant apps with row-level security.
- Deploys as a fully managed container on Amazon ECS Fargate behind an Application Load Balancer with no servers to maintain.
Details
Sold by
Categories
Delivery method
Supported services
Delivery option
New delivery option 1
Latest version
Operating system
Linux
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Free trial
Try this product free for 30 days according to the free trial terms set by the vendor. Usage-based pricing is in effect for usage beyond the free trial terms. Your free trial gets automatically converted to a paid subscription when the trial ends, but may be canceled any time before that.
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/unit/hour |
|---|---|---|
Hours | Container Hours | $3.00 |
Dimensions summary
This product uses a single usage-based dimension: Container Hours. You pay for each hour the container runs, billed by actual usage. There are no tiers or fixed commitments. Your cost scales directly with how long the server stays active. The longer you run it, the more hours accrue. This server lets AI agents query a PostgreSQL database in plain English and run read-only optimization checks. Because billing is hourly, your total depends on your own runtime rather than a set plan size.
Top-of-mind questions for buyers
A Container Hour measures each hour the MCP server container runs on AWS. The meter tracks running time only. If the container runs for part of an hour, billing follows the partial runtime by that unit. Multiple running containers each accrue their own hours at the same time.
Charges apply only while the container runs. A fully stopped container does not accrue Container Hours. Underlying AWS infrastructure, such as storage, may still incur separate AWS fees, but the software meter counts running time alone. Your cost tracks the hours the server stays active.
No. Billing depends on how long the container runs, not on how many queries you send or how large your PostgreSQL database is. Running many plain-English queries in one hour costs the same as running few. Only elapsed runtime drives the Container Hours meter.
sqlagent.tech42demo.com
Helpful?
Vendor refund policy
30-free trial offered. Consumption is usage based. To stop charges, cancel the subscription.
Custom pricing options
Request a private offer to receive a custom quote.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
New delivery option 1
Supported services: Learn more
- Amazon ECS
Container image
Containers are lightweight, portable execution environments that wrap server application software in a filesystem that includes everything it needs to run. Container applications run on supported container runtimes and orchestration services, such as Amazon Elastic Container Service (Amazon ECS) or Amazon Elastic Kubernetes Service (Amazon EKS). Both eliminate the need for you to install and operate your own container orchestration software by managing and scheduling containers on a scalable cluster of virtual machines.
Version release notes
Initial release
Additional details
Usage instructions
Refer following product guide: https://tech42-text2sql-mcp-deployment-asset.s3.us-east-1.amazonaws.com/tech42-text2sql-mcp-deployment-guide.docx.pdf
Resources
Vendor resources
Support
Vendor support
Contact us at support@tech42consulting.com or visit our website at tech42consulting.com
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
The official Splunk remote MCP server is built to help you unlock data potential in Splunk Cloud Platform with the AI and Agentic tools of your choice. Seamlessly integrate advanced analytics and intelligent automation to gain deeper insights, enhance operational efficiency, and drive informed decisions. Leverage a trusted, Splunk supported solution designed for optimal performance and unparalleled data utilization within your Splunk Cloud Platform environment. Rest assured, your data remains safe and secure, with robust controls honoring your existing Role Based Access Control (RBAC) policies. Maximize your data's impact with cutting edge AI and flexible agentic capabilities.
Structured agent access to Elasticsearch: Query indices using natural language via a standardized protocol -- no custom APIs needed
falcon-mcp enables seamless communication between AI agents and the CrowdStrike Falcon platform. Deployable directly onto Amazon Bedrock AgentCore, it provides programmatic access to Falcon data for agentic workflows and accelerating AI-native security automation.
Build GraphQL APIs & MCP Servers for all your data sources in minutes, deploy them in seconds, and run them securely and efficiently as fully managed SaaS. Whether backends are public or private, SQL or NoSQL, REST or SOAP/XML, or other GraphQL APIs, your team can deliver a flexible GraphQL API layer in days, not weeks or months. APIs are concise and declarative; they run as SaaS with built-in performance, cost, and reliability optimizations.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.