Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@tibero-mcp search tables by comment for 주문 and describe the sales order table"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
tibero-mcp is a Model Context Protocol server that lets AI agents such as Claude Code, Codex and Cursor explore and query a Tibero database. It is built for the way agents actually work on enterprise and public-sector schemas: find the right table from a Korean comment, understand its keys, write a query, check the plan, and never change data by accident.
Safe by default. Tibero ignores the JDBC read-only flag and has no SET TRANSACTION READ ONLY, so the server enforces it itself. Only SELECT and WITH run, one statement per call, SELECT … FOR UPDATE is refused, and every read is rolled back. The tool that writes does not even exist unless you turn writes on.
Schema discovery that reads comments. In many Tibero schemas the comments are the only documentation. Search tables and columns by comment (주문, 납기), and get columns, primary, unique and foreign keys and indexes for a table in one call.
Results an agent can use. Typed JSON (numbers stay numbers, dates are ISO strings, LOBs are clipped), a hard row cap with a truncated flag and a next_offset to continue from, statement timeouts, execution plans as a readable tree, and errors that say what to try next.
No driver hunting. The official TmaxTibero JDBC driver (com.tmaxtibero:tbjdbc8, GPG-signed on Maven Central) is downloaded on first run, checked against a pinned SHA-1 and cached. No proprietary jar in this repository, no CLASSPATH to set.
Ready to run alongside other agents. stdio or Streamable HTTP, a connection that reconnects by itself, and a process that exits cleanly when the client goes away.
Verified against Tibero 6 using the 7.2.6 driver.
Related MCP server: Oracle DB MCP Server
You need Python 3.12+, uv, Java 8+ and network access to Maven Central on first run.
Clone and configure
git clone https://github.com/jdk1021/tibero-mcp.git
cd tibero-mcp
cp env.example .env # host, dbname, user, password
uv syncRegister with your client. Claude Code:
claude mcp add -s user tibero -- uv --directory /path/to/tibero-mcp run tibero-mcpClaude Desktop, Cursor and other JSON-configured clients, passing settings as env instead of .env:
{
"mcpServers": {
"tibero": {
"command": "uv",
"args": ["--directory", "/path/to/tibero-mcp", "run", "tibero-mcp"],
"env": {
"TIBERO_HOST": "db.example.com",
"TIBERO_PORT": "8629",
"TIBERO_DBNAME": "tibero",
"TIBERO_USER": "app_reader",
"TIBERO_PASSWORD": "…"
}
}
}
}Ask your agent something like "Which tables hold order dates? Show the structure of the sales order table."
To share one server between several agents, run it over HTTP and point clients at http://127.0.0.1:8000/mcp:
uv run tibero-mcp --transport streamable-http --port 8000The HTTP transport has no authentication and binds to 127.0.0.1 by default. Keep it there, or put it behind something that authenticates.
Tool | What it does |
| Schemas with table and view counts; system schemas only on request |
| Tables and views with comments and row estimates, filtered by text in the name or comment; paged |
| Columns (type, nullability, default, comment), primary, unique and foreign keys, indexes |
| Columns across a schema matched by name or comment, with full types such as |
| One |
| Execution plan as an indented tree, plus per-step cost, cardinality and predicates |
| DML, DDL or a PL/SQL block, committed on success. Registered only when |
Variable | Default | Notes |
| required | |
|
| |
| required; database name (SID) | |
| required | |
|
|
|
|
| upper bound per call |
|
| seconds; |
| use a driver jar you already have instead of downloading | |
| pick a specific JDK or JRE |
Environment variables win over .env in the working directory. The driver is cached in $XDG_CACHE_HOME/tibero-mcp (default ~/.cache/tibero-mcp).
Layer | What it stops |
Tool surface | No |
Statement check | Anything but |
Transaction | Every read ends in a rollback |
Your account | Everything else. A function called from a |
uv sync
uv run ruff check . && uv run ruff format --check .
uv run pytestUnit tests need neither a database nor a JVM. See CONTRIBUTING.md.
MIT for this project. The Tibero JDBC driver is distributed by TmaxTibero under its own license and is not included here. This project is not affiliated with or endorsed by TmaxTibero; Tibero is a trademark of TmaxTibero Co., Ltd.
Show a table's columns (type, nullability, default, comment), keys, foreign keys and indexes.
Inputs: table (required), schema. Returns: object
Show the optimizer's execution plan as an indented tree, plus per-step cost, cardinality and access/filter predicates exactly as Tibero reports them.
Inputs: sql (required). Returns: object
List schemas that own tables or views visible to the connected user, with object counts.
Inputs: include_system. Returns: object
List tables (and views) in a schema with their comments and approximate row counts.
Inputs: offset, schema, search, include_views. Returns: object
Run a read-only query and return columns and rows. truncated is true when more rows exist.
Inputs: sql (required), offset, params, max_rows. Returns: object
Find columns across a schema by name or comment, e.g. '주문' or 'ORDER_DT'. Results are paged.
Inputs: keyword (required), offset, schema, max_rows, +1 more. Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 6 tools
Each tool targets a distinct step in database exploration: schema listing, table listing, table description, column search, querying, and plan explanation. The only near-overlap (describe_table vs search_columns) is clearly separated by scope: one table's structure versus schema-wide column lookup.
Four tools follow a clean verb_noun pattern (list_schemas, list_tables, describe_table, search_columns), but query and explain are bare verbs without a noun. The deviation is minor and the names remain unambiguous.
Six tools is well-scoped for a read-only database exploration server, with no redundant or filler tools. Each tool maps to a clear workflow stage from discovery to query execution.
The surface covers a full discovery-to-execution lifecycle: schemas, tables, columns, search, query, and explain plan. Minor gaps exist, such as standalone index/constraint exploration or procedure/function listing, but agents can work around these via describe_table and query.
Query and update Teable records, manage tables, and access the Teable API with AI agents.
Astra DB tools for agents: schema, find, vector search, guarded writes, and interactive views.
PostgreSQL, MySQL, and SQL Server in one session. 26 read-only MCP tools for AI agents.
Query, explore, and manage your databases through natural conversation.