oracle-mcp-server-helper

Official

Enable live Oracle schema tools for agents

Authororacle-devrel
Version1.0.0
Installs0

System Documentation

What problem does it solve?

You need a safe, consistent way for an LLM agent to inspect and query a live Oracle database schema during inference, without forcing the entire project to depend on an external MCP server transport.

Core Features & Use Cases

  • LangChain tool scaffolding: Creates BaseTool subclasses for list_tables, describe_table, run_sql, and vector_search that call Oracle via oracledb.
  • Configurable tool safety: Supports sql_mode with a default read_only posture and guardrails against mutating SQL unless explicitly enabled.
  • Agent-ready tool registry: Provides a cached tool_registry.py so an agent loop can load tools efficiently with a stable schema surface.

Quick Start

Configure your database connection in target_dir/.env (DB_DSN, DB_USER, DB_PASSWORD) and ask your agent tier to bind the tools returned by target_dir/src/<package_slug>/tool_registry.py.

Dependency Matrix

Required Modules

oracledb>=2.5langchain-core>=0.3langchain-community>=0.3

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: oracle-mcp-server-helper
Download link: https://github.com/oracle-devrel/oracle-ai-developer-hub/archive/main.zip#oracle-mcp-server-helper

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.