prest
PostgreSQL ➕ REST, low-code, simplify and accelerate development, ⚡ instant, realtime, high-performance on any Postgres application, existing or new, MCP server
The pREST MCP server exposes PostgreSQL databases through both REST and Model Context Protocol interfaces, enabling AI agents to query and interact with Postgres data without writing backend code. It automatically generates CRUD endpoints, supports custom SQL queries with safe parameter binding, and provides read-only MCP access to existing or new databases. Designed for production use, it includes authentication, access control, and multi-database support for PostgreSQL 9.5 and higher.
Key Features
Use Cases
- 01Connecting AI coding assistants like Cursor or Claude to query application databases during development
- 02Exposing legacy PostgreSQL databases to AI agents without refactoring existing schemas
- 03Rapid prototyping of data-driven applications with instant API endpoints for database tables
- 04Building low-code backends where AI agents need read access to production or development databases
- 05Integrating TimescaleDB time-series data into AI workflows through MCP-compatible interfaces
- 06Providing controlled database access to AI tools while maintaining security through ACLs and read-only MCP mode
Related MCP Servers
View moremarkitdown
Python tool for converting files and office documents to Markdown.
firecrawl
The context API to search, scrape, and interact with the web at scale. 🔥
prompts.chat
f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.
langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
prest — FAQ
What is the pREST MCP server?+
pREST is a production-ready server that automatically generates both REST and Model Context Protocol (MCP) APIs on top of PostgreSQL databases. It provides instant CRUD operations, custom SQL queries, and read-only MCP endpoints without requiring you to write backend code.
How do I install and configure pREST?+
Install pREST via Docker, Homebrew (prestd), or Go, then configure it by setting the PREST_PG_URL or DATABASE_URL environment variable to point to your PostgreSQL database. Full configuration options for auth, ACL, and MCP are documented at docs.prestd.com.
Which AI clients and editors work with pREST?+
pREST's MCP endpoint works with AI clients that support the Model Context Protocol, including Cursor, Claude Desktop, and other MCP-compatible tools. The REST API can be consumed by any HTTP client or AI agent.
Do I need API keys or a PostgreSQL database to use pREST?+
You need a PostgreSQL database (version 9.5 or higher) with connection credentials. No additional API keys are required, though you can configure authentication and access control as needed for production deployments.
Is pREST free and open source?+
Yes, pREST is open source and available on GitHub. Contributors are asked to sign a Contributor License Agreement (CLA).
How does pREST prevent SQL injection in custom queries?+
pREST uses bound parameters (sqlVal, sqlList helpers) that send user values out-of-band to Postgres, preventing them from being parsed as SQL. Interpolated values are screened and rejected if they contain quotes, comments, or SQL keywords.
How do I install prest?+
Open the source repository on GitHub and follow its README. prest is a mcp server — MCP Agents Market links you directly to the official repo.
Is prest free?+
prest is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.