schemacrawler-ai
Enables natural language schema queries — explore tables, keys, procedures, and get SQL help fast
Open the source (opens github.com) https://github.com/schemacrawler/schemacrawler-ai
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
- Needs credentials: SCHCRWLR_ADDITIONAL_CONFIG, SCHCRWLR_DATABASE_PASSWORD, SCHCRWLR_DATABASE_USER, SCHCRWLR_JDBC_URL. Use a key with the least access you can.
What it is
MCP servers from io.github.schemacrawler.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
oci package (stdio)
schemacrawler/schemacrawler-ai:18.0.2-1
From the server's entry in the official MCP Registry
Settings it asks for
SCHCRWLR_MCP_SERVER_TRANSPORT· MCP Server transport type - valid values are 'http' or 'stdio', defaulting to 'stdio'.SCHCRWLR_DATABASE_USERsecret · Database user name. Can be optional depending on the database connection type.SCHCRWLR_DATABASE_PASSWORDsecret · Database user password. Can be optional depending on the database connection type.SCHCRWLR_JDBC_URLsecret · Optional JDBC URL for database connection. If nonblank, server, host, port, and database are ignored. Credentials may still be supplied separately.SCHCRWLR_SERVER· SchemaCrawler database connector identifier, for example, 'sqlserver' or 'sqlite'. Required if the JDBC URL is blank or unset.SCHCRWLR_HOST· Database host. Defaults to the connector's host default. Used only if the JDBC URL is blank or unset.SCHCRWLR_PORT· Database port. Valid decimal values from 1024 through 65535 are used; otherwise the connector's default port is retained. Used only if the JDBC URL is blank…SCHCRWLR_DATABASE· Optional database name or connector-specific database value. Used only if the JDBC URL is blank or unset.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: 'minimum', 'standard', 'detailed', or 'maximum'. Defaults to 'standard'; unset or unrecognized values also use…SCHCRWLR_LOG_LEVEL· Java logging level. Defaults to 'INFO'. Java logging names such as 'SEVERE', 'WARNING', 'INFO', 'CONFIG', 'FINE', 'FINER', 'FINEST', 'ALL', and 'OFF', and…
Related
-
GitHub MCP server
MCP serversGitHub's official MCP server. It lets an agent read and work with repositories, issues and pull requests.
https://api.githubcopilot.com/mcp/ -
Apify MCP server
MCP serversLets an agent run Apify's ready-made scrapers to pull data from websites, search engines, maps and social platforms.
-
Official MCP Registry
MCP serversThe MCP project's own registry of public MCP servers, so you can look for a connector before building one.
-
MCP reference servers
MCP serversSmall example servers from the MCP project (filesystem, git, fetch, memory and more) that show how MCP works.
-
Connect MCP servers to Claude Code
MCP serversAnthropic's guide to adding MCP servers to Claude Code, with examples of local and remote servers.
-
Playwright MCP
MCP serversLets an agent drive a real browser: open pages, click, fill in forms and read what's on screen.
claude mcp add playwright npx @playwright/mcp@latest