oci-documentation-mcp-server: Instructions file for Codex

AGENTS.md

oci-documentation-mcp-server AGENTS.md is an instructions file for Codex, OpenCode from jin38324/oci-documentation-mcp-server. It costs 1,526 tokens per session, scanned A, original, MIT.

Project instructions for a Python MCP server that searches and reads Oracle Cloud Infrastructure documentation. Oracle Cloud Infrastructure is Oracle's cloud-computing platform, and MCP lets an AI agent call tools provided by a server.

In plain words
What is it for?
They help maintain tools that search Oracle Help Center results or fetch a documentation page and return selected lines as structured content.
Why use it?
They explain the server's purpose, public tools, technology choices, and file layout so changes stay focused and consistent.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is jin38324/oci-documentation-mcp-server's own configuration. It tells Codex and OpenCode how to work on oci-documentation-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything oci-documentation-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jin38324/oci-documentation-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jin38324/oci-documentation-mcp-server/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/jin38324/oci-documentation-mcp-server

Made for: Codex, OpenCode.

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 oci-documentation-mcp-server AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jin38324/oci-documentation-mcp-server/agents-md.svg)](https://agentmods.dev/instructions/jin38324/oci-documentation-mcp-server/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/jin38324/oci-documentation-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/jin38324/oci-documentation-mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,526 This file is loaded in full into every session.
When invoked 1,526 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 5.1 $0.01526 $0.01526
Opus 5 $0.00763 $0.00763
Sonnet 5 $0.00305 $0.00305
Haiku 4.5 $0.00153 $0.00153

Measured 6d ago against content hash 2f612b3fd796, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

oci-documentation-mcp-server AGENTS.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 6d 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.

AGENTS.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Project overview

This repository contains oci-documentation-mcp-server, a Python Model Context Protocol (MCP) server for searching and reading Oracle Cloud Infrastructure documentation.

The server exposes two public MCP tools:

  • oci_search_documentation(search_phrase: str, limit: int, page: int): searches Oracle Help Center (OHC) page results and returns pagination plus documentation URLs.
  • oci_read_documentation(url: str, start_index: int, max_lines: int): fetches one docs.oracle.com HTML page, converts it to markdown, indexes it by line number, and returns a line window as JSON.

Keep the project small. Prefer direct, well-scoped helpers over new framework layers.

Technology choices

  • Package and environment manager: uv.
  • Runtime: Python 3.10+.
  • MCP framework: standalone fastmcp.FastMCP.
  • HTTP client: httpx.
  • Data validation: pydantic v2.
  • HTML extraction and markdown conversion: beautifulsoup4 and markdownify.
  • Logging: loguru, controlled by FASTMCP_LOG_LEVEL.
  • Build backend: hatchling.
  • Static and test tooling configured in pyproject.toml: ruff, pyright, pytest, pytest-asyncio, pytest-mock, bandit, and commitizen.

Use uv commands for dependency and lock-file maintenance.

File map

  • oci_documentation_mcp_server/server.py: MCP server entrypoint, FastMCP setup, tool registration, CLI argument handling, URL validation, and high-level tool error handling.
  • oci_documentation_mcp_server/ohc_search.py: OHC Search API client, request parameter validation, pagination/result models, and search response normalization.
  • oci_documentation_mcp_server/util.py: documentation page fetching, HTML-to-markdown conversion, line-window formatting, table-of-contents extraction, related-link extraction, and in-process document cache.
  • oci_documentation_mcp_server/models.py: shared public Pydantic models.
  • tests/test_mcp.py: live/integration tests for MCP tool functions. These tests access real Oracle documentation and OHC search endpoints.
  • tests/REST API doc.md: local reference document for the OHC Search API.
  • README.md: user-facing overview and MCP configuration examples.
  • pyproject.toml: package metadata, runtime dependencies, script entrypoint, and tool configuration.
  • uv.lock: locked dependency graph generated by uv lock.

Read the full file on GitHub · 121 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. 6d ago First seen · 121 lines · 1,526 tokens per session scan A 2f612b3fd796

Subscribe to this mod's changes

oci-documentation-mcp-server AGENTS.md is an instructions file published in the GitHub repository jin38324/oci-documentation-mcp-server (11 stars, last pushed 3mo ago), licensed MIT. It adds 1,526 tokens to every session, about $0.0076 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.

Related

Other instructions, from other repositories