saudi-open-data-mcp: Instructions file for Codex

AGENTS.md

saudi-open-data-mcp AGENTS.md is an instructions file for Codex, OpenCode from raheb77/saudi-open-data-mcp. It costs 639 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for a server that gives AI tools access to selected Saudi government datasets. MCP is the connection format used by the server; the instructions focus on separating source connectors, data cleanup, metadata, storage, and monitoring.

In plain words
What is it for?
Use them when adding supported data sources, normalizing datasets, updating the registry, changing MCP tools, or working on the container and local server modes.
Why use it?
They keep raw government data access separate from the tools that AI calls. This makes datasets more consistent, the supported sources clear, and the server easier to check and operate.

Instructions file for CodexOpenCode

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

This is raheb77/saudi-open-data-mcp's own configuration. It tells Codex and OpenCode how to work on saudi-open-data-mcp 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 saudi-open-data-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to raheb77/saudi-open-data-mcp. 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/raheb77/saudi-open-data-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/raheb77/saudi-open-data-mcp

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 saudi-open-data-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/raheb77/saudi-open-data-mcp/agents-md.svg)](https://agentmods.dev/instructions/raheb77/saudi-open-data-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/raheb77/saudi-open-data-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/raheb77/saudi-open-data-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 639 This file is loaded in full into every session.
When invoked 639 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00639 $0.00639
Opus 5 $0.00319 $0.00319
Sonnet 5 $0.00128 $0.00128
Haiku 4.5 $0.00064 $0.00064

Measured 7d ago against content hash 662f5fbbf668, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

saudi-open-data-mcp 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 7d 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 · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidance

Scope

This repository is a production-minded foundation for saudi-open-data-mcp.

  • MCP is the interface layer, not the core value
  • the core value is source isolation, normalized dataset contracts, registry-backed metadata, health checks, and reliable AI-facing tool interfaces
  • the current baseline is the 0.4.0a1 internal/evaluator-controlled alpha
  • current source scope includes SAMA, three narrow stats.gov.sa macro datasets, one Ministry of Finance fiscal dataset, and one narrow data.gov.sa pilot dataset
  • the deployed runtime is container-first streamable HTTP, while stdio remains supported for local development and command-based host integration

Approved Structure

Keep changes inside the approved repository layout under src/saudi_open_data_mcp/:

  • connectors/
  • normalization/
  • registry/
  • storage/
  • tools/
  • resources/
  • observability/
  • security/
  • server.py
  • config.py
  • cli.py

Do not add service packages, prompt packages, or alternate architectural areas.

Boundary Rules

  • tools/ must not import raw connectors directly
  • MCP-facing modules must not contain raw source access logic
  • raw payload fetching must not happen inside tools/, resources/, or server.py
  • normalization logic must stay inside normalization/
  • registry metadata and health metadata must come from registry/
  • all source access must go through connector abstractions
  • all normalized outputs must use typed Pydantic models
  • no LLM, semantic search, or query rewriting in the core path
  • use httpx for new/default HTTP access paths; do not add new alternate HTTP clients. The existing narrow SAMA transport fallback is a compatibility exception, not a pattern to spread.
  • only approved official sources may be accessed

Implementation Rules

  • keep placeholders minimal, deterministic, and importable when they are still necessary
  • do not add fake examples, fake benchmarks, or half-implemented business logic
  • keep README.md, AGENTS.md, docs/CHANGELOG.md, TASKS.md, and server.json aligned when changing supported surfaces or runtime posture

Read the full file on GitHub · 72 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. 7d ago First seen · 72 lines · 639 tokens per session scan A 662f5fbbf668

Subscribe to this mod's changes

saudi-open-data-mcp AGENTS.md is an instructions file published in the GitHub repository raheb77/saudi-open-data-mcp (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 639 tokens to every session, about $0.0032 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

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens