# schemacrawler-ai This MCP server lets an AI agent inspect database schemas, including tables, keys, and procedures, and answer SQL questions in plain language. - MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 12 - Author: schemacrawler - License: not stated · policy=link-only · description only; the file stays with the author - Source: https://github.com/schemacrawler/SchemaCrawler-AI - Updated: 2026-10-22 - HTML: https://affpapa.org/en/nevibecode/mcp/schemacrawler-ai ## What it does schemacrawler-ai connects a database to an AI agent through MCP. The agent can inspect tables, relationships, and keys, look up stored procedures, and discuss SQL using natural-language requests. The server runs from the Docker image `schemacrawler/schemacrawler-ai:17.16.0-1`. Its setup passes the MCP transport, database user and password, JDBC URL, and `SCHCRWLR_SERVER` value into the container. The server cannot connect without database credentials and `SCHCRWLR_JDBC_URL`. Setup commands are provided for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and other listed platforms. In Claude Code, the MCP entry uses `claude mcp add` and starts Docker over `stdio`. ## Requirements - Needs: Docker - Environment variables: `SCHCRWLR_MCP_SERVER_TRANSPORT`, `SCHCRWLR_DATABASE_USER`, `SCHCRWLR_DATABASE_PASSWORD`, `SCHCRWLR_JDBC_URL`, `SCHCRWLR_SERVER`, `SCHCRWLR_HOST`, `SCHCRWLR_PORT`, `SCHCRWLR_DATABASE`, `SCHCRWLR_DATABASE_ALIAS`, `SCHCRWLR_DATABASE_DESCRIPTION` — keys and tokens: ask the human for the values, never commit them or put them in shared files. ## Install ### Claude Code (native platform) **Platform CLI** ```bash claude mcp add --env SCHCRWLR_MCP_SERVER_TRANSPORT= --env SCHCRWLR_DATABASE_USER= --env SCHCRWLR_DATABASE_PASSWORD= --env SCHCRWLR_JDBC_URL= --env SCHCRWLR_SERVER= --transport stdio schemacrawler-ai -- docker run -i --rm -e SCHCRWLR_MCP_SERVER_TRANSPORT -e SCHCRWLR_DATABASE_USER -e SCHCRWLR_DATABASE_PASSWORD -e SCHCRWLR_JDBC_URL -e SCHCRWLR_SERVER schemacrawler/schemacrawler-ai:17.16.0-1 ``` Replace <…> with your own values. 8 more environment variables are in the server README ### Codex **Platform CLI** ```bash codex mcp add schemacrawler-ai --env SCHCRWLR_MCP_SERVER_TRANSPORT= --env SCHCRWLR_DATABASE_USER= --env SCHCRWLR_DATABASE_PASSWORD= --env SCHCRWLR_JDBC_URL= --env SCHCRWLR_SERVER= -- docker run -i --rm -e SCHCRWLR_MCP_SERVER_TRANSPORT -e SCHCRWLR_DATABASE_USER -e SCHCRWLR_DATABASE_PASSWORD -e SCHCRWLR_JDBC_URL -e SCHCRWLR_SERVER schemacrawler/schemacrawler-ai:17.16.0-1 ``` Replace <…> with your own values. 8 more environment variables are in the server README ### Cursor **Config file** File `.cursor/mcp.json`: ```json { "mcpServers": { "schemacrawler-ai": { "command": "docker", "args": [ "run", "-i", "--rm", "-e", "SCHCRWLR_MCP_SERVER_TRANSPORT", "-e", "SCHCRWLR_DATABASE_USER", "-e", "SCHCRWLR_DATABASE_PASSWORD", "-e", "SCHCRWLR_JDBC_URL", "-e", "SCHCRWLR_SERVER", "schemacrawler/schemacrawler-ai:17.16.0-1" ], "env": { "SCHCRWLR_MCP_SERVER_TRANSPORT": "", "SCHCRWLR_DATABASE_USER": "", "SCHCRWLR_DATABASE_PASSWORD": "", "SCHCRWLR_JDBC_URL": "", "SCHCRWLR_SERVER": "" } } } } ``` Replace <…> with your own values. 8 more environment variables are in the server README ### GitHub Copilot **Config file** File `.vscode/mcp.json`: ```json { "servers": { "schemacrawler-ai": { "type": "stdio", "command": "docker", "args": [ "run", "-i", "--rm", "-e", "SCHCRWLR_MCP_SERVER_TRANSPORT", "-e", "SCHCRWLR_DATABASE_USER", "-e", "SCHCRWLR_DATABASE_PASSWORD", "-e", "SCHCRWLR_JDBC_URL", "-e", "SCHCRWLR_SERVER", "schemacrawler/schemacrawler-ai:17.16.0-1" ], "env": { "SCHCRWLR_MCP_SERVER_TRANSPORT": "", "SCHCRWLR_DATABASE_USER": "", "SCHCRWLR_DATABASE_PASSWORD": "", "SCHCRWLR_JDBC_URL": "", "SCHCRWLR_SERVER": "" } } } } ``` Replace <…> with your own values. 8 more environment variables are in the server README ### Gemini CLI **Platform CLI** ```bash gemini mcp add -e SCHCRWLR_MCP_SERVER_TRANSPORT= -e SCHCRWLR_DATABASE_USER= -e SCHCRWLR_DATABASE_PASSWORD= -e SCHCRWLR_JDBC_URL= -e SCHCRWLR_SERVER= schemacrawler-ai docker run -i --rm -e SCHCRWLR_MCP_SERVER_TRANSPORT -e SCHCRWLR_DATABASE_USER -e SCHCRWLR_DATABASE_PASSWORD -e SCHCRWLR_JDBC_URL -e SCHCRWLR_SERVER schemacrawler/schemacrawler-ai:17.16.0-1 ``` Replace <…> with your own values. 8 more environment variables are in the server README ## When to use it - inspect database tables and keys - look up stored procedures by asking the agent - get SQL guidance from the schema - query database structure in natural language ## Example prompts - Show the tables and keys in the connected database. - Find stored procedures related to orders. - Suggest the SQL query I need for this task using the database schema. ## Similar - [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 392262 - [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33989 - [World Monitor](https://affpapa.org/en/nevibecode/mcp/world-monitor.md) — MCP server · ★ 89609 - [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81163 - [Front-End Checklist](https://affpapa.org/en/nevibecode/mcp/front-end-checklist.md) — MCP server · ★ 74569 - [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89899 --- 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