Oracle MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ORACLE_SID | No | Oracle SID | |
| ORACLE_HOST | No | Oracle database host | |
| ORACLE_PORT | No | Oracle database port | |
| ORACLE_USER | No | Oracle database username | |
| ORACLE_PASSWORD | No | Oracle database password | |
| ORACLE_TNS_NAME | No | Oracle TNS name | |
| ORACLE_SERVICE_NAME | No | Oracle service name | |
| ORACLE_DEFAULT_SCHEMA | No | Default schema if different from user | |
| ORACLE_CONNECTION_STRING | No | Oracle easy connect string in format hostname:1521/service_name |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| execute_queryC | Execute a SQL query on the Oracle database |
| list_tablesB | List tables from specified schema or all accessible schemas |
| describe_tableC | Get table structure including columns, data types, and constraints |
| get_table_indexesC | Get indexes for a specific table |
| get_table_constraintsC | Get constraints (primary keys, foreign keys, unique, check) for a table |
| list_schemasB | List all schemas in the database |
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 has a clearly distinct purpose with no ambiguity: describe_table focuses on column structure, execute_query handles SQL queries, get_table_constraints retrieves constraint details, get_table_indexes covers indexes, list_schemas enumerates schemas, and list_tables lists tables. There is no overlap in functionality that would cause misselection.
All tools follow a consistent verb_noun pattern using snake_case: describe_table, execute_query, get_table_constraints, get_table_indexes, list_schemas, and list_tables. The naming is predictable and readable throughout the set.
With 6 tools, the server is well-scoped for database exploration and querying. Each tool earns its place by covering essential operations like schema listing, table metadata retrieval, and query execution, without being too sparse or bloated.
The tool set provides strong coverage for database inspection and querying, including CRUD-like operations via execute_query and metadata access. Minor gaps exist, such as no explicit tools for data manipulation (e.g., insert, update, delete) or transaction management, but agents can work around these using execute_query for most workflows.