apex-mcp CLAUDE.md

apex-mcp CLAUDE.md is an instructions file for coding agents from TechFernandesLTDA/apex-mcp. It costs 4,047 tokens per session, scanned A, original, MIT.

Repository instructions for working on apex-mcp, an MCP server that lets AI coding clients create Oracle APEX applications through code.

In plain words
What is it for?
Use them when installing, running, testing, or changing the apex-mcp server and its connections to Oracle APEX.
Why use it?
They give an AI coding assistant the project’s setup, run commands, and testing requirements, including which tests need an Oracle database.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/techfernandesltda/apex-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/TechFernandesLTDA/apex-mcp

Wrote 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.

agentmods badge for apex-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/techfernandesltda/apex-mcp/claude-md.svg)](https://agentmods.dev/instructions/techfernandesltda/apex-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/techfernandesltda/apex-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/techfernandesltda/apex-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,047 This file is loaded in full into every session.
When invoked 4,047 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.04047 $0.04047
Opus 5 $0.02024 $0.02024
Sonnet 5 $0.00809 $0.00809
Haiku 4.5 $0.00405 $0.00405

Measured 5d ago against content hash 0a986c344301, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

apex-mcp 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 5d 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.

CLAUDE.md · 280 lines

How it starts

The opening of the file, as written. The whole thing — 280 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.

What This Is

apex-mcp is an MCP (Model Context Protocol) server for Oracle APEX 24.2 that exposes 116+ tools to AI clients (Claude, GPT, Gemini, Cursor, VS Code). It generates APEX applications programmatically via PL/SQL using the wwv_flow_imp_page.* internal API (same as APEX's own import/export).

Build & Run

# Install
pip install -e ".[dev]"

# Run (stdio — default for local AI clients)
python -m apex_mcp
apex-mcp                    # equivalent, via entry point

# Run with HTTP transport
python -m apex_mcp --transport streamable-http --port 8000
python -m apex_mcp --transport sse --port 9000

Testing

# Unit tests only (no Oracle DB required)
pytest tests/ -v -m "not integration"

# All tests (requires live Oracle ADB + env vars)
pytest tests/ -v

# Single test file
pytest tests/test_session.py -v

# Single test
pytest tests/test_ids.py::test_unique_ids -v

Tests require ORACLE_DB_USER, ORACLE_DB_PASS, ORACLE_DSN, ORACLE_WALLET_DIR, ORACLE_WALLET_PASSWORD, APEX_WORKSPACE_ID, APEX_SCHEMA, APEX_WORKSPACE_NAME env vars for integration tests.

Architecture

Core Singletons (module-level instances)

  • db (apex_mcp/db.py) -- ConnectionManager singleton. Thread-safe Oracle connection via oracledb thin driver + mTLS wallet. Has auto-reconnect on transient ORA errors (03113, 03114, 12170, 25408), dry-run mode (logs PL/SQL without executing), and batch mode (queues PL/SQL, executes in one commit). Also provides safe_col() / column_exists() for APEX version-safe column access with caching.
  • session (apex_mcp/session.py) -- ImportSession singleton. Tracks all components (pages, regions, items, buttons, LOVs, auth schemes, charts, processes, branches, dynamic actions) created during the apex_create_app() to apex_finalize_app() lifecycle. Tools use it to resolve cross-references like region IDs. Thread-safe via threading.RLock.
  • ids (apex_mcp/ids.py) -- IdGenerator singleton. Produces unique IDs (base 8,900,000,000,000,000 + random salt + counter) with a named registry to avoid collisions within a session. Reset on each apex_create_app() call.

Read the full file on GitHub · 280 lines

Changes

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.

  1. 5d ago First seen · 280 lines · 4,047 tokens per session scan A 0a986c344301

Subscribe to this mod's changes

apex-mcp CLAUDE.md is an instructions file published in the GitHub repository TechFernandesLTDA/apex-mcp (15 stars, last pushed 3mo ago), licensed MIT. It adds 4,047 tokens to every session, about $0.0202 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 2026-08-30.