mcp_forge: Instructions file for Codex

AGENTS.md

mcp_forge AGENTS.md is an instructions file for Codex, OpenCode from mlzoo/mcp_forge. It costs 420 tokens per session, scanned A, original, MIT.

Instructions for an MCP service built with Python, FastAPI, and Uvicorn that provides mock parking-lot lookup endpoints. MCP is a way for AI tools to connect to services and call their functions.

In plain words
What is it for?
Developing the parking lookup API and MCP endpoint, running the local server, checking formatting and code quality, and understanding the project's setup limitations.
Why use it?
They explain how to run, format, test, and inspect the service, including the important fact that it has no test files yet and needs restarting after changes.

Instructions file for CodexOpenCode

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

This is mlzoo/mcp_forge's own configuration. It tells Codex and OpenCode how to work on mcp_forge 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 mcp_forge configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mlzoo/mcp_forge. 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/mlzoo/mcp_forge/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/mlzoo/mcp_forge

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 mcp_forge AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mlzoo/mcp_forge/agents-md/github.svg)](https://agentmods.dev/instructions/mlzoo/mcp_forge/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mlzoo/mcp_forge/agents-md"><img src="https://agentmods.dev/badge/instructions/mlzoo/mcp_forge/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp_forge AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/mlzoo/mcp_forge/agents-md"><img src="https://agentmods.dev/badge/instructions/mlzoo/mcp_forge/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 420 This file is loaded in full into every session.
When invoked 420 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 $0.00420 $0.00420
Opus 5.5 $0.00168 $0.00168
Sonnet 5.5 $0.00084 $0.00084
Haiku 4.5 $0.00042 $0.00042

Measured 2mo ago against content hash 155a9a15777d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp_forge 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 2mo 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 · 23 lines

What it actually says

AGENTS.md

Cursor Cloud specific instructions

This is a Python 3.12 FastAPI + FastAPI-MCP service (a parking-lot lookup example). It is managed with the uv package manager. Standard commands live in the Makefile and README.md; prefer those.

Service overview

  • Single service: main.py starts a Uvicorn server on 0.0.0.0:5000.
    • REST docs (Swagger UI): http://localhost:5000/docs
    • MCP endpoint (SSE): http://localhost:5000/mcp
    • Endpoints: POST /parking/nearby and POST /parking/info (mock data, no external services or secrets needed).

Run / lint / test

  • Run dev server: make dev (equivalently uv run python main.py). It is NOT a hot-reload server; restart the process after code changes.
  • Lint: uv run ruff check . and uv run ruff format --check . (the make check target also runs uv lock --locked and full pre-commit, which needs network to install hook envs).
  • Tests: make test / uv run python -m pytest. There is currently no tests/ directory, so pytest exits with code 5 ("no tests collected") — this is expected, not a failure.

Non-obvious gotchas

  • pyproject.toml declares a heavy, unused dependency ttt-video (git) that transitively pulls torch, torchvision, xformers, triton, transformers, etc. uv sync installs all of it (multi-GB), even though main.py never imports it. Do not be surprised by the large .venv.
  • The app code uses Traditional Chinese strings; ensure UTF-8 output when inspecting responses.
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. 2mo ago First seen · 23 lines · 420 tokens per session scan A 155a9a15777d

Subscribe to this mod's changes

mcp_forge AGENTS.md is an instructions file published in the GitHub repository mlzoo/mcp_forge (206 stars, last pushed 4mo ago), licensed MIT. It adds 420 tokens to every session, about $0.0017 per session on Opus 5.5. 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.

Related

mcp_forge AGENTS.md compared with instructions from other repositories

mcp_forge AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mcp_forge AGENTS.mdmlzoo/mcp_forgeInstructions file2064mo agoMITA420Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k2d agoMITA4,313Codex, OpenCode