PluginBench
MCP Server
Active

io.github.schemacrawler/schemacrawler-ai MCP Server

io.github.schemacrawler/schemacrawler-ai

Natural language database schema exploration and SQL assistance via AI agents

RepositoryRegistry
How to choose

What this kind of tool is for

  • Query, inspect, or seed a database without writing a one-off script.
  • Let your agent look up schema details before it writes migration code.
  • Move a small dataset between tools without leaving the terminal.

How to compare servers like this

Engine match:
Confirm it speaks your exact database and version, not just the family.
Access scope:
Read-only connections are the safe default — start there before granting writes.
Safety rails:
Check whether destructive statements need an explicit confirmation before they run.
Maintenance signal:
Database drivers change; a recently updated tool is less likely to break mid-query.

This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.

What is the io.github.schemacrawler/schemacrawler-ai MCP server?

SchemaCrawler AI is an MCP Server that enables AI agents to interactively query and explore database schema metadata using natural language. Built on SchemaCrawler, it provides schema discovery and comprehension capabilities for tables, keys, procedures, and SQL assistance.

SchemaCrawler AI allows AI agents like Claude and Cursor to interrogate your database schema metadata through natural language queries. It leverages SchemaCrawler's database schema discovery capabilities to help you explore table structures, relationships, procedures, and get SQL help without manual schema inspection.

How to install io.github.schemacrawler/schemacrawler-ai

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • SCHCRWLR_MCP_SERVER_TRANSPORT

    MCP Server transport type - valid values are 'http' or 'stdio', defaulting to 'stdio'.

  • SCHCRWLR_DATABASE_USER
    secret

    Database user name. Can be optional depending on the database connection type.

  • SCHCRWLR_DATABASE_PASSWORD
    secret

    Database user password. Can be optional depending on the database connection type.

  • SCHCRWLR_JDBC_URL

    JDBC URL for database connection. If this is provided, the server, host, port and database are not used.

  • SCHCRWLR_SERVER

    SchemaCrawler database plugin, for example, 'sqlserver' or 'sqlite'. Used only if the JDBC URL is not provided.

  • SCHCRWLR_HOST

    Database host. Defaults to localhost. Used only if the JDBC URL is not provided.

  • SCHCRWLR_PORT

    Database port. Defaults to the default port for the server type. Used only if the JDBC URL is not provided.

  • SCHCRWLR_DATABASE

    Database to connect to (optional). Used only if the JDBC URL is not provided.

  • SCHCRWLR_DATABASE_ALIAS

    Optional stable alias used to identify this database server in MCP instructions and tool results.

  • SCHCRWLR_DATABASE_DESCRIPTION

    Optional description of this database server, included in MCP instructions and the about_database response.

  • SCHCRWLR_INFO_LEVEL

    How much database metadata to retrieve. Values are 'minimum', 'standard', 'detailed' or 'maximum'.

  • SCHCRWLR_LOG_LEVEL

    Logging verbosity level. Values are 'SEVERE', 'WARNING', 'INFO', 'CONFIG', or 'FINE'.

  • SCHCRWLR_EXCLUDE_TOOLS

    MCP Server tools to exclude, as a comma-separated list.

~/Library/Application Support/Claude/claude_desktop_config.json
JSON config
{
  "mcpServers": {
    "schemacrawler-ai": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "schemacrawler/schemacrawler-ai:17.15.7-1"
      ],
      "env": {
        "SCHCRWLR_MCP_SERVER_TRANSPORT": "<YOUR_SCHCRWLR_MCP_SERVER_TRANSPORT>",
        "SCHCRWLR_DATABASE_USER": "<YOUR_SCHCRWLR_DATABASE_USER>",
        "SCHCRWLR_DATABASE_PASSWORD": "<YOUR_SCHCRWLR_DATABASE_PASSWORD>",
        "SCHCRWLR_JDBC_URL": "<YOUR_SCHCRWLR_JDBC_URL>",
        "SCHCRWLR_SERVER": "<YOUR_SCHCRWLR_SERVER>",
        "SCHCRWLR_HOST": "<YOUR_SCHCRWLR_HOST>",
        "SCHCRWLR_PORT": "<YOUR_SCHCRWLR_PORT>",
        "SCHCRWLR_DATABASE": "<YOUR_SCHCRWLR_DATABASE>",
        "SCHCRWLR_DATABASE_ALIAS": "<YOUR_SCHCRWLR_DATABASE_ALIAS>",
        "SCHCRWLR_DATABASE_DESCRIPTION": "<YOUR_SCHCRWLR_DATABASE_DESCRIPTION>",
        "SCHCRWLR_INFO_LEVEL": "<YOUR_SCHCRWLR_INFO_LEVEL>",
        "SCHCRWLR_LOG_LEVEL": "<YOUR_SCHCRWLR_LOG_LEVEL>",
        "SCHCRWLR_EXCLUDE_TOOLS": "<YOUR_SCHCRWLR_EXCLUDE_TOOLS>"
      }
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • Schema metadata queries — Query database tables, keys, procedures, and other schema metadata using natural language
  • SQL assistance — Get help with SQL queries and schema-related questions

Use cases

  • Explore database table structures and relationships using natural language questions
  • Discover stored procedures and their parameters in your database
  • Get SQL query suggestions based on your schema structure
  • Understand foreign key relationships and constraints interactively
  • Generate schema documentation and analysis through conversational queries

io.github.schemacrawler/schemacrawler-ai MCP server FAQ

What is SchemaCrawler AI?

SchemaCrawler AI is an MCP Server that lets AI agents query your database schema using natural language, exploring tables, keys, procedures, and providing SQL assistance.

Is SchemaCrawler AI free?

SchemaCrawler AI is licensed under the Business Source License 1.1 (BUSL-1.1). Non-production use is permitted, but production or commercial use requires a separate commercial agreement.

How do I install SchemaCrawler AI in Cursor or Claude?

Install via Docker using the OCI image: schemacrawler/schemacrawler-ai:17.15.7-1. See the SchemaCrawler AI MCP Server Usage repository for detailed setup instructions.

What database metadata can I query?

You can query tables, columns, keys, procedures, constraints, and other schema metadata from your database.

Do I need to authenticate with my database?

Yes, you need to provide database connection credentials to allow the MCP Server to access your database schema.

Where can I find more information?

Visit the SchemaCrawler website at https://www.schemacrawler.com/ or the SchemaCrawler AI MCP Server Usage repository for detailed documentation.

README (reference)

Source of truth, from the repository.

<!-- markdownlint-disable MD041 -->

:star: Star it :arrow_heading_up: if you love it!

Build Docker Pulls Docker MCP Pulls GitHub Repo stars

<img src="https://github.com/schemacrawler/SchemaCrawler-Usage/blob/98e442d9a957070d45e87109d5b32d7f17b62927/schemacrawler-website/src/site/resources/images/schemacrawler_logo.png?raw=true" height="100px" width="100px" valign="middle"/> SchemaCrawler AI

[!NOTE]

About

SchemaCrawler AI provides an MCP Server to allow AI agents to have an interactive way to interrogate your database schema metadata. It is based on SchemaCrawler, which is a free database schema discovery and comprehension tool.

Licensing

SchemaCrawler AI is licensed under the Business Source License 1.1 (BUSL-1.1) license.

This project may be distributed together with third-party components such as JDBC drivers and other libraries. Unless explicitly stated otherwise, the Business Source License 1.1 applies only to the SchemaCrawler AI MCP Server source code authored for this repository. All third-party components included in source or binary distributions are licensed separately by their respective copyright holders. See the documentation or the distribution package for third-party license information.

Under the Business Source License 1.1, you are free to read, modify, and redistribute the source code, subject to the license terms. However, production or commercial use of SchemaCrawler AI MCP Server is restricted except as permitted by a separate commercial agreement. If you are interested in production or commercial use please see the SchemaCrawler website.

Support

SchemaCrawler AI is not supported, unless you purchase a support incident. Please see Guidelines for Support for details.

Related MCP servers

Four x402 tools: endpoint checks, extraction, evidence verification, domain intelligence.

View repository →

ECB data for AI agents — rates, yields, inflation, money supply, and 100+ datasets. No API key.

3
TypeScript
MIT
View repository →

Classification service to seamlessly retrieve SOC codes for job titles and descriptions.

View repository →
FAfabric-dw logo

fabric-dw

Active

MCP server for administering, querying, and optimizing Microsoft Fabric Data Warehouses and SQL Analytics Endpoints.

9
Python
MIT
View repository →

AI presentation and report generation: slides, diagrams, PPTX export, live preview MCP App.

1100+ actively deploying VC funds and 608 disclosed LPs, with live investor signals

0
View repository →