Skip to content
mcp/harbor
Grok

schemacrawler ai for Grok

io.github.schemacrawler/schemacrawler-ai

Enables natural language schema queries — explore tables, keys, procedures, and get SQL help fast

client:Grok transport:stdio runtime:oci

Install schemacrawler ai in Grok

.mcp.json (in your project root)

Held in this page only — never stored, logged, or sent anywhere but back to your screen. 

{
  "mcpServers": {
    "schemacrawler-ai": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "schemacrawler/schemacrawler-ai:17.15.6-1"
      ],
      "env": {
        "SCHCRWLR_MCP_SERVER_TRANSPORT": "<SCHCRWLR_MCP_SERVER_TRANSPORT>",
        "SCHCRWLR_DATABASE_USER": "<SCHCRWLR_DATABASE_USER>",
        "SCHCRWLR_DATABASE_PASSWORD": "<SCHCRWLR_DATABASE_PASSWORD>",
        "SCHCRWLR_JDBC_URL": "<SCHCRWLR_JDBC_URL>",
        "SCHCRWLR_SERVER": "<SCHCRWLR_SERVER>",
        "SCHCRWLR_HOST": "<SCHCRWLR_HOST>",
        "SCHCRWLR_PORT": "<SCHCRWLR_PORT>",
        "SCHCRWLR_DATABASE": "<SCHCRWLR_DATABASE>",
        "SCHCRWLR_INFO_LEVEL": "<SCHCRWLR_INFO_LEVEL>",
        "SCHCRWLR_LOG_LEVEL": "<SCHCRWLR_LOG_LEVEL>",
        "SCHCRWLR_EXCLUDE_TOOLS": "<SCHCRWLR_EXCLUDE_TOOLS>"
      }
    }
  }
}

Grok Build reads Claude Code's .mcp.json and Claude Desktop's config unchanged, so a server you have already set up there needs nothing new. The Grok web app and X integration do not take custom servers. Grok docs

schemacrawler ai in other clients

schemacrawler ai MCP server