Cubrid Mcp Server
A Model Context Protocol (MCP) server for CUBRID database — enabling LLMs to inspect schemas and execute read-only queries via pycubrid.
- Transport
- Not stated
- Package
- —
- Registry id
- —
No install snippet on purpose. A working MCP config is a command, its arguments and an environment block — the last two are where API keys live, so this catalogue never stores them and cannot publish them. Follow the link above for the authors' own instructions.
The server is a Model Context Protocol server for the CUBRID database, enabling LLMs to inspect schemas and run read-only queries via the pycubrid driver. It is read-only by default with a SQL whitelist that only allows SELECT, SHOW, DESC, DESCRIBE, EXPLAIN, and WITH statements. It is schema-aware, with twelve tools covering table discovery, column metadata, indexes, serials, class hierarchy, row counts, execution plans, and health checks.
It supports multi-database: one server process can serve several CUBRID databases with independent settings. It is operations-friendly, with all logging to stderr, sanitized errors, and an opt-in audit log that never logs raw SQL. It is licensed under MIT and part of the CUBRID Lab open-source initiative.
Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.