# DBeast PostgreSQL MCP Hooks an AI assistant up to PostgreSQL for schema browsing, read-only queries, security and performance audits. - MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 9 - Author: snss10 - License: MIT · policy=link-only · description only; the file stays with the author - Source: https://github.com/snss10/DBeast - Updated: 2026-08-10 - HTML: https://affpapa.org/en/nevibecode/mcp/dbeast-postgresql-mcp ## What it does DBeast is a local stdio MCP server written in Python. Your editor or desktop assistant spawns it as a child process, and the connection details arrive as environment variables: `DATABASE_URL`, `DB_HOST`, `DB_PORT`, `DB_USER`, `DB_PASSWORD`. There is no HTTP endpoint to host, so nothing new lands in your infrastructure. Rather than one wide-open `execute_sql`, it ships 21 tools grouped into ten areas. `get_schema` and `dependency_analysis` map tables, columns and relationships; `execute_query` handles reads with a row cap applied for you; `analyze_query` and `query_optimizer` cover plans and index suggestions; `analyze_impact` previews what a write would touch; `security_audit` and `sensitive_data_scan` look at roles and likely PII; `maintenance_analysis`, `data_quality_report` and `replication_status` fill in the rest. You need Python 3.11+ and PostgreSQL 12+. Two install routes exist: from source with `pip install -e .`, or the image `ghcr.io/snss10/dbeast:2.0.2`. The container path is the shorter one for Claude, Codex and Gemini CLI, where `claude mcp add`, `codex mcp add` and `gemini mcp add` carry the variables for you. Cursor, GitHub Copilot and Windsurf take a JSON block instead. Skip the credentials and the server has nothing to connect to. ## Requirements - Needs: Docker - Environment variables: `DATABASE_URL`, `DB_HOST`, `DB_PORT`, `DB_USER`, `DB_PASSWORD`, `DB_NAME`, `AWS_SECRET_NAME`, `AWS_REGION` — keys and tokens: ask the human for the values, never commit them or put them in shared files. - Works with: PostgreSQL ## Install ### Claude Code (native platform) **Platform CLI** ```bash claude mcp add --env DATABASE_URL= --env DB_HOST= --env DB_PORT= --env DB_USER= --env DB_PASSWORD= --transport stdio dbeast-postgresql-mcp -- docker run -i --rm -e DATABASE_URL -e DB_HOST -e DB_PORT -e DB_USER -e DB_PASSWORD ghcr.io/snss10/dbeast:2.0.2 ``` Replace <…> with your own values. 3 more environment variables are in the server README ### Codex **Platform CLI** ```bash codex mcp add dbeast-postgresql-mcp --env DATABASE_URL= --env DB_HOST= --env DB_PORT= --env DB_USER= --env DB_PASSWORD= -- docker run -i --rm -e DATABASE_URL -e DB_HOST -e DB_PORT -e DB_USER -e DB_PASSWORD ghcr.io/snss10/dbeast:2.0.2 ``` Replace <…> with your own values. 3 more environment variables are in the server README ### Cursor **Config file** File `.cursor/mcp.json`: ```json { "mcpServers": { "dbeast-postgresql-mcp": { "command": "docker", "args": [ "run", "-i", "--rm", "-e", "DATABASE_URL", "-e", "DB_HOST", "-e", "DB_PORT", "-e", "DB_USER", "-e", "DB_PASSWORD", "ghcr.io/snss10/dbeast:2.0.2" ], "env": { "DATABASE_URL": "", "DB_HOST": "", "DB_PORT": "", "DB_USER": "", "DB_PASSWORD": "" } } } } ``` Replace <…> with your own values. 3 more environment variables are in the server README ### GitHub Copilot **Config file** File `.vscode/mcp.json`: ```json { "servers": { "dbeast-postgresql-mcp": { "type": "stdio", "command": "docker", "args": [ "run", "-i", "--rm", "-e", "DATABASE_URL", "-e", "DB_HOST", "-e", "DB_PORT", "-e", "DB_USER", "-e", "DB_PASSWORD", "ghcr.io/snss10/dbeast:2.0.2" ], "env": { "DATABASE_URL": "", "DB_HOST": "", "DB_PORT": "", "DB_USER": "", "DB_PASSWORD": "" } } } } ``` Replace <…> with your own values. 3 more environment variables are in the server README ### Gemini CLI **Platform CLI** ```bash gemini mcp add -e DATABASE_URL= -e DB_HOST= -e DB_PORT= -e DB_USER= -e DB_PASSWORD= dbeast-postgresql-mcp docker run -i --rm -e DATABASE_URL -e DB_HOST -e DB_PORT -e DB_USER -e DB_PASSWORD ghcr.io/snss10/dbeast:2.0.2 ``` Replace <…> with your own values. 3 more environment variables are in the server README ## When to use it - map an unfamiliar database before touching it - find out why a dashboard query drags - see how many rows a bulk update would hit before running it - check roles, grants and what the public schema exposes - spot duplicate rows and null-heavy columns ## Example prompts - Show me the schema for the `orders` table with its indexes - Explain the execution plan for the dashboard query and suggest indexes - Audit the public schema for security and maintenance issues ## Similar - [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89408 - [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89433 - [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16717 - [PostHog MCP Server](https://affpapa.org/en/nevibecode/mcp/posthog-mcp-server.md) — MCP server · ★ 40409 - [dbx](https://affpapa.org/en/nevibecode/mcp/dbx.md) — MCP server · ★ 27669 - [Metabase](https://affpapa.org/en/nevibecode/mcp/metabase.md) — MCP server · ★ 49845 --- NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md