Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/git-scarrow/oracle-mcp-server/claude-mdgit clone --depth 1 https://github.com/git-scarrow/oracle-mcp-serverWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/git-scarrow/oracle-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/git-scarrow/oracle-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/git-scarrow/oracle-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01171 | $0.01171 |
| Opus 5 | $0.00585 | $0.00585 |
| Sonnet 5 | $0.00234 | $0.00234 |
| Haiku 4.5 | $0.00117 | $0.00117 |
Grade A, and why
oracle-mcp-server CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is an Oracle MCP Server that provides a flexible interface for AI assistants to interact with Oracle databases through the Model Context Protocol. The server supports multiple schemas and provides comprehensive database introspection and query capabilities.
Common Development Commands
Running the Server
# Install dependencies
npm install
# Start the MCP server
npm start
# Run in development mode with file watching
npm run dev
Testing Connection
# Set environment variables first
export ORACLE_CONNECTION_STRING=hostname:1521/service_name
export ORACLE_USER=your_username
export ORACLE_PASSWORD=your_password
# Run the server
npm start
Architecture
MCP Server Implementation
- Framework: Model Context Protocol (MCP) SDK
- Database: Oracle Database with
oracledbclient library - Connection: Supports multiple authentication methods (Easy Connect, TNS, individual components)
- Transport: stdio (stdin/stdout for JSON-RPC communication)
Core Components
-
Main Server (
src/index.js):- Extends MCP Server with Oracle database integration
- Implements 6 tools for database operations
- Supports multiple Oracle connection methods
- Automatically converts PostgreSQL-style parameters to Oracle bind variables
-
Available Tools:
execute_query- Execute any SQL query with parameter binding (supports SELECT, INSERT, UPDATE, DELETE, etc.)list_tables- List tables from specified schema or all accessible schemasdescribe_table- Get table structure and column details (searches all schemas if not specified)get_table_indexes- View indexes on a specific table (searches all schemas if not specified)get_table_constraints- View constraints (PK, FK, unique, check) for a tablelist_schemas- List all accessible schemas in the database
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 146 lines · 1,171 tokens per session scan A d1dfe81018e4
oracle-mcp-server CLAUDE.md is an instructions file published in the GitHub repository git-scarrow/oracle-mcp-server (10 stars, last pushed 2mo ago), licensed MIT. It adds 1,171 tokens to every session, about $0.0059 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
plan-forge database.instructions.md
Database patterns for .NET — Dapper/EF Core, parameterized queries, migration strategy.
pg-dash CLAUDE.md
Claude Code instructions for indiekitai/pg-dash, covering pg-dash claude.md, 项目结构, 构建与测试, 发版纪律（强制） and 发版检查清单（每次 npm publish 前必须按序执行）.
jdbc-driver CLAUDE.md
Claude Code instructions for keboola/jdbc-driver, covering claude.md, project overview, build & test commands, jdbc driver and vscode sqltools extension.
MCP-SqlServer CLAUDE.md
Claude Code instructions for Aron-Valenzuela/MCP-SqlServer, covering claude.md, project overview, setup (for each user), 1. install dependencies and 2. configure claude desktop.
plsql-intelligence AGENTS.md
Instructions for MuhDur/plsql-intelligence, covering agents.md — plsql-intelligence, founder constraints (plan.md §3, non-negotiable), plan rules to internalize (plan.md §4), rule 1 – absolute (do not ever violate this) and irreversible git & filesystem actions.