What is Ultimate_MCP AGENTS.md?

Repository instructions for coding agents working on Ultimate_MCP, a project with a Python service, React web interface, command-line installer, tests, and deployment files.

Use them when modifying, testing, checking, or deploying the Ultimate_MCP codebase.

They give the agent the project's layout, commands, naming rules, and testing expectations so it can make changes in the expected way.

How Senpai-Sama7/Ultimate_MCP configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Senpai-Sama7/Ultimate_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/Senpai-Sama7/Ultimate_MCP/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Senpai-Sama7/Ultimate_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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/senpai-sama7/ultimate_mcp/agents-md/github.svg)](https://agentmods.dev/instructions/senpai-sama7/ultimate_mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/senpai-sama7/ultimate_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/senpai-sama7/ultimate_mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/senpai-sama7/ultimate_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/senpai-sama7/ultimate_mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 655 This file is loaded in full into every session.

When invoked 655 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.

Model	Per session	Once invoked
Fable 5.1	$0.00655	$0.00655
Opus 5.5	$0.00262	$0.00262
Sonnet 5.5	$0.00131	$0.00131
Haiku 4.5	$0.00065	$0.00065

Measured 2mo ago against content hash d9af6b0af645, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Ultimate_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 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 · 36 lines

How it starts

The opening of the file, as written. The whole thing — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines for Agentic Coding Agents

Project Structure & Module Organization

backend/ contains the FastAPI MCP service; core runtime lives in mcp_server/ and cross-agent glue in agent_integration/. Tests mirror runtime code under backend/tests/ with fixtures in conftest.py. frontend/ is the Vite + React client (src/components, src/hooks, src/services). cli/ ships the Node installer via bin/ultimate-mcp.js and supporting modules in src/. Refer to deployment/ for Compose assets, scripts/ for automation, docs/ for architecture notes, and demo/full_demo.py for the supervised walk-through.

Build, Test, and Development Commands

Setup: python scripts/setup.py [--ci] (prepares backend/.venv and installs Node deps)
Run API: source backend/.venv/bin/activate && uvicorn mcp_server.enhanced_server:app --reload --port 8000 --host 0.0.0.0
Run UI: cd frontend && npm run dev
Run tests: backend/.venv/bin/pytest backend/tests
Run single test: backend/.venv/bin/pytest backend/tests/test_file.py::test_function_name
Lint Python: backend/.venv/bin/ruff check backend
Type check Python: backend/.venv/bin/mypy backend
Lint frontend: cd frontend && npm run lint

Coding Style & Naming Conventions

Python: 4-space indentation, full type hints, 100-char limit (enforced by black/ruff)
Naming: snake_case for modules/functions, PascalCase for classes, descriptive MCP tool IDs
Error handling: Use specific exceptions, log appropriately, don't suppress silently
Imports: Standard library first, then third-party, then local; alphabetical within groups
Frontend: ESLint enforced; React components in PascalCase, hooks/utilities in camelCase

Testing Guidelines

Mandatory coverage: backend/.venv/bin/pytest backend/tests --cov=backend/mcp_server --cov=backend/agent_integration --cov-report=term-missing
Backend tests spin up Neo4j test container via Docker; ensure Docker daemon is running
Validate workflow: python demo/full_demo.py --base-url http://localhost:8000 --auth-token <token> then python scripts/smoke_test.py
CLI/UI updates: Run cd cli && npm run smoke and record manual checks

Read the full file on GitHub · 36 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.

2mo ago First seen · 36 lines · 655 tokens per session scan A d9af6b0af645

Subscribe to this mod's changes

Ultimate_MCP AGENTS.md is an instructions file published in the GitHub repository Senpai-Sama7/Ultimate_MCP (0 stars, last pushed 11mo ago), licensed MIT. It adds 655 tokens to every session, about $0.0026 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 2026-09-01.

Ultimate_MCP AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
Ultimate_MCP AGENTS.mdSenpai-Sama7/Ultimate_MCP	Instructions file	0	11mo ago	MIT	A	655	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

Ultimate_MCP: Instructions file for Codex