pgEdge announces general availability of the pgEdge MCP Server for Postgres, enabling developers to build secure, production-ready Agentic AI applications with full deployment flexibility and enterprise-grade Postgres capabilities.
Quick Intel
pgEdge, the leading open source enterprise Postgres company, today announced general availability of the pgEdge MCP Server for Postgres. This full-featured and production-ready MCP server is designed for developers building Agentic AI applications in environments with strict requirements for high availability, security, data sovereignty, and global deployment.
Unlike other available MCP servers, the pgEdge MCP Server for Postgres works with both new and existing databases running any standard version of Postgres (v14 and newer). It offers flexible deployment options including on-premises (even air-gapped), self-managed cloud, or a managed cloud service via pgEdge Cloud. This deployment flexibility, combined with the enterprise-grade capabilities of pgEdge Enterprise Postgres, allows developers to take their Agentic AI applications from prototyping all the way to production on compliant and secure infrastructure.
"Most MCP servers today aren't built with enterprise requirements in mind," said David Mitchell, CEO of pgEdge. "We designed the pgEdge MCP Server for Postgres to deliver the flexibility of open source with the performance, security, and deployment control enterprises need—whether that's in the cloud, on-prem, or in air-gapped environments. It's a critical step toward making AI infrastructure production-ready."
The pgEdge MCP Server for Postgres works with AI application builders and code generators such as Claude Code, Cursor, Windsurf, and VS Code Copilot. It supports frontier models from OpenAI and Anthropic in addition to locally hosted models using Ollama, LM Studio, and other OpenAI API compatible products.
As with other pgEdge Postgres products, the pgEdge MCP Server for Postgres is fully open source under the Postgres license and is fully supported by pgEdge’s leading team of Postgres contributors and expert developers.
Key Features of pgEdge MCP Server for Postgres
The MCP server includes several enterprise-focused capabilities that set it apart:
Full Schema Introspection The server pulls detailed information about database structure beyond basic table and column names, including primary keys, foreign keys, indexes, column types, and constraints. This allows the LLM to reason about the data model rather than querying it blindly.
Configurable Read-Only and Read/Write Support Read-only and read/write modes can be enabled via a simple switch.
Built-in Security The server supports stdio, HTTP, and HTTPS with TLS, user and token authentication, and enforces read-only mode by default.
Multi-Database Support It supports multiple databases such as development, staging, and production environments, with easy switching between them.
Performance Metrics Exposure The server exposes pg_stat_statements and other data so the LLM can provide performance optimization recommendations.
Additional Enhancements in This GA Release
The general availability release introduces several important improvements:
pgEdge will be attending the MCP Dev Summit 2026 on April 2-3 in New York at booth S13 and will be conducting live demos.
Product Availability
The pgEdge MCP Server for Postgres is available as a free download to all Postgres users and is now also available within the pgEdge Cloud managed service. pgEdge customers with paid subscriptions for pgEdge Enterprise Postgres or pgEdge Distributed Postgres receive support at no extra cost. For self-hosted and self-managed deployments, product documentation and downloads are available through pgEdge resources.
pgEdge, the leading open source enterprise Postgres company, delivers open-source, 100% Postgres infrastructure for Agentic AI and enterprise applications that demand high availability, reliability, and data sovereignty. Its mission is to make it easy to build, deploy, and manage enterprise-grade applications at scale on Postgres. Headquartered in Northern Virginia, pgEdge is trusted by organizations including Bertelsmann, Qube RT, Jobot, and U.S. government agencies. Its investors include Akamai Technologies, Inc., Qube RT, Rally Ventures, Sands Capital Ventures, Grotech Ventures, and Sand Hill East.
TechIntelPro empowers B2B technology decision-makers with the latest industry trends, deep insights, leadership perspectives and actionable intelligence to drive both organizational and professional milestones—and thrive on the tech pulse.