OracleDB MCP Server

An MCP server for interacting with Oracle Database, enabling SQL generation and data retrieval via LLM prompts.

- This project will installMCP - Model Context Protocol Server, that provides configured Oracle Database Table/Columns as context to LLM's.
- Using this we can enable LLMs to interact with Oracle Database, Generate SQL Statements and Return Results using LLM prompts.

- Install package

pip install oracledb_mcp_server

- Configuration details for Claud Desktop

{ "mcpServers": { "oracledb_mcp_server":{ "command": "uv", "args": ["run","oracledb_mcp_server"], "env": { "DEBUG":"True", "COMMENT_DB_CONNECTION_STRING":"oracle+oracledb://USERNAME:PASSWORD@IP:PORT/?service_name=SERVICENAME", "DB_CONNECTION_STRING":"oracle+oracledb://USERNAME:PASSWORD@IP:PORT/?service_name=SERVICENAME", "TABLE_WHITE_LIST":"ACCOUNTS,CUS_ACC_RELATIONS,CUSTOMERS", "COLUMN_WHITE_LIST":"ACCOUNTS.ACC_AAD_ID,CUS_ACC_RELATIONS.CAR_CUS_ID,CUS_ACC_RELATIONS.CAR_AAD_ID,CUSTOMERS.CUS_ID" } } } }

- List of available environment variables

- DEBUG: Enable debug logging (optional default is False)
- COMMENT_DB_CONNECTION_STRING: Oracle DB connection String for comments. (required)
- DB_CONNECTION_STRING: Oracle DB connection String for execution of queries. (required)
- TABLE_WHITE_LIST: White Listed table names in list format ["table1", "table2"] (required)
- COLUMN_WHITE_LIST: White Listed table-column names in list format ["table.column1", "table.column2"] (required)
- QUERY_LIMIT_SIZE: Default value is 10 records if not provided(optional default is 10)

npx @modelcontextprotocol/inspector uv --directory "D:\\MyDev\\mcp\\oracledb_mcp_server" run -m oracledb_mcp_server

Contributions are welcome.
Please feel free to submit a Pull Request.

This project is licensed under the terms of the MIT license.

Multi-database agent access (PostgreSQL, SQLite, MySQL, Oracle, SQL Server) with batch queries, pre-configured connections, and SQLGlot-enforced read-only safety

MCP servers that give AI clients safe, structured access to SQL databases. One installable package per database engine. Every package exposes the same minimal two-tool surface, execute_sql and search_objects, with guardrails on by default: read-only mode, row caps, and statement timeouts.

Guardrails for natural-language database queries.

Provides read-only access to Apache Iceberg tables via Apache Impala, allowing LLMs to inspect schemas and execute queries.

MCP server that gives AI agents deep understanding of contemporary or legacy relational databases.

A bridge for AI assistants to directly query and explore Microsoft SQL Server databases.

Production safe MCP server that gives AI agents direct access to MySQL databases.

MCP server for MySQL/MariaDB — schema inspection, queries, and data manipulation for AI assistants

Provides AI agents with direct access to query, search, and analyze MySQL databases.

A read-only MySQL database server for LLMs to inspect schemas and execute queries.