tibero-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| JAVA_HOME | No | Select a specific JDK or JRE. | |
| TIBERO_HOST | Yes | Tibero database host (required). | |
| TIBERO_PORT | No | Tibero database port. Defaults to 8629. | 8629 |
| TIBERO_USER | Yes | Tibero database user (required). | |
| TIBERO_DBNAME | Yes | Tibero database name (SID) (required). | |
| TIBERO_JDBC_JAR | No | Use an existing JDBC driver jar instead of downloading it. | |
| TIBERO_MAX_ROWS | No | Upper bound on the number of rows returned per call. Defaults to 500. | 500 |
| TIBERO_PASSWORD | Yes | Tibero database password (required). | |
| TIBERO_READ_ONLY | No | Set to false to register the execute tool for DML, DDL or PL/SQL blocks. Defaults to true. | true |
| TIBERO_QUERY_TIMEOUT | No | Statement timeout in seconds; 0 disables it. Defaults to 30. | 30 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Tibero database at localhost:8629/tibero, connected as TIBERO_USER (read-only). Tibero speaks an Oracle-compatible SQL dialect: use ROWNUM for row limits, DUAL for scalar selects, and the ALL_* dictionary views. Unqualified names resolve to the connected user's schema. Start with list_tables or search_columns to find objects (comments are often in Korean), then describe_table before writing queries. Results are capped; when truncated is true, call again with offset=next_offset.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_schemasA | List schemas that own tables or views visible to the connected user, with object counts. |
| list_tablesB | List tables (and views) in a schema with their comments and approximate row counts. |
| describe_tableB | Show a table's columns (type, nullability, default, comment), keys, foreign keys and indexes. |
| search_columnsA | Find columns across a schema by name or comment, e.g. '주문' or 'ORDER_DT'. Results are paged. |
| queryA | Run a read-only query and return columns and rows. |
| explainA | Show the optimizer's execution plan as an indented tree, plus per-step cost, cardinality and access/filter predicates exactly as Tibero reports them. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
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.